INDEX

Explanations

words related to historical events or topics

oai_token-act-pair · gpt-3.5-turbo

references to history as a subject or theme

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

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

enger

-0.73

igans

-0.67

leased

-0.67

Introduced

-0.66

achment

-0.64

¾

-0.62

weeney

-0.62

unsigned

-0.62

autions

-0.61

arling

-0.60

POSITIVE LOGITS

 buffs

1.06

 textbooks

1.01

 lesson

0.92

orians

0.91

 books

0.90

 repeats

0.83

making

0.78

orian

0.76

 repeating

0.76

 museums

0.75

Activations Density 0.045%

words related to historical events or topics

references to history as a subject or theme

No Comments

No Known Activations