INDEX

Explanations

mentions of the word "Queen."

oai_token-act-pair · gpt-3.5-turbo

mentions of royalty, specifically the term "Queen"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

odcast

-0.75

razil

-0.73

kson

-0.72

sych

-0.68

aping

-0.65

iance

-0.65

aneous

-0.64

ERSON

-0.62

letcher

-0.62

herer

-0.61

POSITIVE LOGITS

 Anne

1.00

Queen

0.93

stown

0.89

pin

0.88

 Majesty

0.78

pins

0.78

Anne

0.77

 Mother

0.77

 Queen

0.76

esses

0.75

Activations Density 0.009%

mentions of the word "Queen."

mentions of royalty, specifically the term "Queen"

No Comments

No Known Activations