INDEX

Explanations

references to specific years

oai_token-act-pair · gpt-3.5-turbo

mentions of specific years

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

 cumbers

-0.74

 showc

-0.74

creen

-0.72

ktop

-0.71

ecast

-0.67

 collar

-0.67

 zipper

-0.66

 encl

-0.66

 contag

-0.66

 externalToEVAOnly

-0.66

POSITIVE LOGITS

long

1.12

ning

0.99

ago

0.97

lings

0.96

book

0.94

nings

0.93

ns

0.91

Ago

0.91

 olds

0.87

books

0.80

Activations Density 0.090%

references to specific years

mentions of specific years

No Comments

No Known Activations