INDEX

Explanations

questions related to actions or decisions

oai_token-act-pair · gpt-3.5-turbo

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

onz

-0.69

tun

-0.69

iza

-0.66

gem

-0.66

WAYS

-0.66

bis

-0.64

legram

-0.64

ldom

-0.62

bow

-0.62

charg

-0.61

POSITIVE LOGITS

 happens

0.99

 happen

0.96

 distinguishes

0.90

 happened

0.89

 transpired

0.89

 awaits

0.84

?),

0.82

?",

0.82

0.80

 constitutes

0.77

Activations Density 0.055%

questions related to actions or decisions

No Comments

No Known Activations