INDEX

Explanations

references to the word "jam" in various contexts

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "jam" in various contexts

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

 Equality

-0.69

 reconc

-0.69

 Highlander

-0.69

ģ«

-0.68

 Mutual

-0.66

 Affairs

-0.66

 Nations

-0.66

 Advantage

-0.65

Reply

-0.62

Sham

-0.62

POSITIVE LOGITS

ming

1.48

mers

1.14

mer

1.09

bling

0.99

monds

0.93

bley

0.92

nit

0.91

enegger

0.88

ilton

0.88

bles

0.87

Activations Density 0.017%

references to the word "jam" in various contexts

occurrences of the word "jam" in various contexts

No Comments

No Known Activations