INDEX

Explanations

terms related to self or identity

oai_token-act-pair · gpt-3.5-turbo

references to olfactory senses and related terms

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 Snapchat

-0.76

 Samoa

-0.74

OPLE

-0.72

 Hole

-0.66

 Archdemon

-0.65

 Insider

-0.63

 sclerosis

-0.63

Shot

-0.62

 Crus

-0.62

UAL

-0.62

POSITIVE LOGITS

onso

1.18

ornia

1.03

actory

1.01

roth

0.96

rd

0.93

ried

0.93

licks

0.88

ighters

0.87

sg

0.87

ayette

0.86

Activations Density 0.026%

terms related to self or identity

references to olfactory senses and related terms

No Comments

No Known Activations