INDEX

Explanations

proper nouns or names of individuals or organizations

oai_token-act-pair · gpt-3.5-turbo

references to governmental and organizational entities

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

 ..."

-0.66

 dstg

-0.64

âķĲâķĲ

-0.63

cult

-0.61

chest

-0.59

ãĥ¬

-0.59

Els

-0.58

piring

-0.58

 monog

-0.58

 Tibetan

-0.57

POSITIVE LOGITS

 countered

0.94

 recalled

0.86

 responded

0.83

 additionally

0.82

 spokesman

0.81

 spokeswoman

0.80

 cautioned

0.78

 also

0.77

anwhile

0.76

 spokesperson

0.76

Activations Density 0.682%

proper nouns or names of individuals or organizations

references to governmental and organizational entities

No Comments

No Known Activations