INDEX

Explanations

non-English characters, potentially indicating it is looking for specific languages or unique character patterns

oai_token-act-pair · gpt-3.5-turbo

character sequences or special characters that suggest a specific encoding or language

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

perse

-0.75

 poaching

-0.70

 livest

-0.70

 scarce

-0.69

 dexter

-0.68

comfort

-0.65

 nutrit

-0.64

 dipping

-0.64

 traff

-0.64

Wan

-0.64

POSITIVE LOGITS

ÑĮ

1.31

ÑĢ

1.24

Ð¾

1.22

Ð°

1.20

Ð²

1.12

Ðµ

1.12

Ð¸

1.11

Ñģ

1.10

ments

1.08

Ð¾Ð

1.07

Activations Density 0.009%

non-English characters, potentially indicating it is looking for specific languages or unique character patterns

character sequences or special characters that suggest a specific encoding or language

No Comments

No Known Activations