INDEX

Explanations

mentions of the politician Bernie Sanders

oai_token-act-pair · gpt-3.5-turbo

mentions of a specific individual, Bernie Sanders

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ocaust

-0.83

 Hitchcock

-0.75

 Kinnikuman

-0.73

ories

-0.71

omaly

-0.70

————

-0.64

 cavity

-0.64

obe

-0.64

 pregn

-0.64

othy

-0.62

POSITIVE LOGITS

 supporters

1.13

1.10

 Sanders

1.08

 Supporters

1.01

 supporter

1.01

 delegates

0.97

Sanders

0.96

 backers

0.94

']

0.91

 Caucus

0.91

Activations Density 0.021%

mentions of the politician Bernie Sanders

mentions of a specific individual, Bernie Sanders

No Comments

No Known Activations