INDEX

Explanations

mentions of the word "Palin"

oai_token-act-pair · gpt-3.5-turbo

mentions of Sarah Palin

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Dickens

-0.68

URI

-0.68

omething

-0.67

ribution

-0.66

ires

-0.65

~~~~~~~~~~~~~~~~

-0.63

Increases

-0.61

ortun

-0.61

reek

-0.60

Ö¼

-0.57

POSITIVE LOGITS

 Palin

1.06

igon

0.81

istani

0.76

tera

0.76

mart

0.72

aska

0.71

ohydrate

0.70

sty

0.70

thood

0.68

isma

0.68

Activations Density 0.011%

mentions of the word "Palin"

mentions of Sarah Palin

No Comments

No Known Activations