INDEX

Explanations

words related to deterioration or decay

oai_token-act-pair · gpt-3.5-turbo

terms related to decay and decomposition

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Gomez

-0.79

cedented

-0.74

 quota

-0.72

 Meadows

-0.70

ace

-0.70

 Solo

-0.70

lio

-0.70

iliated

-0.69

ealous

-0.69

 solo

-0.68

POSITIVE LOGITS

 decay

3.20

 decaying

2.60

 decom

2.56

 Decay

2.55

 decre

1.93

 decomp

1.56

DEC

1.51

 disinteg

1.44

DEC

1.41

 deterior

1.39

Activations Density 0.040%

words related to deterioration or decay

terms related to decay and decomposition

No Comments

No Known Activations