INDEX

Explanations

commands or instructions

oai_token-act-pair · gpt-3.5-turbo

emotive expressions or interjections

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

ividual

-0.76

 redist

-0.74

itably

-0.71

 seeded

-0.69

 descending

-0.67

 domestically

-0.67

 scattering

-0.66

 semic

-0.65

 prevailing

-0.65

 neighb

-0.65

POSITIVE LOGITS

âĢķ

1.08

¹

1.04

£

0.88

Â¯Â¯

0.85

âĻ

0.84

dro

0.83

âĶĢ

0.83

º

0.83

Â·Â·

0.83

say

0.81

Activations Density 0.477%

commands or instructions

emotive expressions or interjections

No Comments

No Known Activations