INDEX

Explanations

references or additional resources indicated by a specific marker

oai_token-act-pair · gpt-3.5-turbo

references to resources and information in a structured format

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

hement

-0.81

umbers

-0.68

sic

-0.66

axy

-0.63

 guts

-0.60

 Luthor

-0.58

 destro

-0.57

otos

-0.56

efe

-0.56

iru

-0.55

POSITIVE LOGITS

ãĥīãĥ©

0.84

References

0.82

âĨĳ

0.80

ÂłÂłÂłÂłÂłÂłÂłÂł

0.76

ÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂłÂł

0.75

========

0.74

Below

0.73

Spoiler

0.72

Past

0.71

pmwiki

0.71

Activations Density 0.130%

references or additional resources indicated by a specific marker

references to resources and information in a structured format

No Comments

No Known Activations