INDEX

Explanations

phrases indicating the presence or absence of information

oai_token-act-pair · gpt-3.5-turbo

phrases expressing doubt or lack of information

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

 towed

-0.77

rive

-0.70

 hire

-0.65

ulo

-0.64

uga

-0.64

âĢ¢âĢ¢âĢ¢âĢ¢

-0.62

 funnel

-0.62

killed

-0.62

 pend

-0.62

hirt

-0.61

POSITIVE LOGITS

 ABOUT

1.01

 about

0.98

 regarding

0.89

 beforehand

0.85

 concerning

0.84

about

0.84

 aloud

0.82

 differently

0.75

 Arabic

0.74

EngineDebug

0.74

Activations Density 0.196%

phrases indicating the presence or absence of information

phrases expressing doubt or lack of information

No Comments

No Known Activations