INDEX

Explanations

specific terms related to examining or investigating various objects or situations

oai_token-act-pair · gpt-3.5-turbo

references to product examinations or evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ń·

-0.74

-+

-0.69

;;

-0.64

å§

-0.62

ario

-0.61

-+-+-+-+

-0.59

uala

-0.59

ĺħ

-0.58

udeb

-0.58

elected

-0.58

POSITIVE LOGITS

 favorably

0.89

 trends

0.87

 closely

0.87

 strengths

0.84

 discrepancies

0.82

 carefully

0.82

 aloud

0.80

 angles

0.79

 patterns

0.78

 archives

0.76

Activations Density 0.669%

specific terms related to examining or investigating various objects or situations

references to product examinations or evaluations

No Comments

No Known Activations