INDEX

Explanations

words related to specific individuals or entities

oai_token-act-pair · gpt-3.5-turbo

occurrences of specific character sequences

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

 litter

-0.69

 negro

-0.62

 pyramid

-0.62

jog

-0.61

 compar

-0.61

 Negro

-0.60

 vulner

-0.60

 mathemat

-0.59

 tuna

-0.59

 township

-0.59

POSITIVE LOGITS

ï¸ı

1.17

worthiness

1.00

ï¸

0.90

hood

0.89

VICE

0.88

sure

0.87

Balt

0.86

İ

0.82

tre

0.82

WARE

0.82

Activations Density 0.416%

words related to specific individuals or entities

occurrences of specific character sequences

No Comments

No Known Activations