INDEX

Explanations

expressions related to necessity, expectation, or assessment

oai_token-act-pair · gpt-3.5-turbo

the necessity of certain actions or conditions

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

opian

-0.77

 fray

-0.66

 Globe

-0.63

Rab

-0.62

 Kore

-0.62

zynski

-0.59

 whirlwind

-0.58

 overlap

-0.57

Jur

-0.57

 limbo

-0.57

POSITIVE LOGITS

leeve

0.98

 able

0.92

fitting

0.86

 done

0.85

fits

0.84

 accounted

0.84

 considered

0.83

 addressed

0.82

 understood

0.81

 careful

0.80

Activations Density 0.099%

expressions related to necessity, expectation, or assessment

the necessity of certain actions or conditions

No Comments

No Known Activations