INDEX

Explanations

mentions of political figures, specifically senators

oai_token-act-pair · gpt-3.5-turbo

occurrences of the title "Senator."

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

phal

-0.69

Company

-0.67

 Siberian

-0.65

ãĥ¼ãĥ³

-0.64

anked

-0.63

tera

-0.61

iHUD

-0.60

heading

-0.60

 upkeep

-0.59

condition

-0.59

POSITIVE LOGITS

iors

0.99

arians

0.95

ileaks

0.91

pai

0.90

eca

0.88

 senator

0.87

 Senator

0.84

ial

0.82

ially

0.79

Downloadha

0.78

Activations Density 0.012%

mentions of political figures, specifically senators

occurrences of the title "Senator."

No Comments

No Known Activations