INDEX

Explanations

mentions of a specific person named Bernie Sanders

oai_token-act-pair · gpt-3.5-turbo

references to Bernie Sanders

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

obar

-0.80

otropic

-0.80

ãĥ¼ãĥĨãĤ£

-0.79

tyr

-0.73

ebin

-0.71

perm

-0.71

odon

-0.70

obe

-0.68

conservancy

-0.68

omaly

-0.67

POSITIVE LOGITS

 Sanders

1.37

Sanders

0.97

 Supporters

0.95

 Bernard

0.89

 supporters

0.86

 Bernie

0.83

Bernie

0.82

INTON

0.81

 supporter

0.77

 Bros

0.77

Activations Density 0.010%

mentions of a specific person named Bernie Sanders

references to Bernie Sanders

No Comments

No Known Activations