INDEX

Explanations

mentions of a specific person, likely related to a political context, named Sanders

oai_token-act-pair · gpt-3.5-turbo

frequent mentions of the name "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

ocaust

-0.83

ocard

-0.78

obar

-0.78

omaly

-0.78

 Seym

-0.74

obe

-0.74

onut

-0.71

odynam

-0.69

 Kinnikuman

-0.66

asus

-0.66

POSITIVE LOGITS

 Sanders

1.10

Sanders

0.98

 Supporters

0.91

 supporters

0.88

 Caucus

0.85

 delegates

0.82

istas

0.80

 Bros

0.80

INTON

0.80

ileaks

0.78

Activations Density 0.010%

mentions of a specific person, likely related to a political context, named Sanders

frequent mentions of the name "Sanders."

No Comments

No Known Activations