INDEX

Explanations

terms addressing audiences in a formal setting

oai_token-act-pair · gpt-3.5-turbo

mentions of "ladies" and "gentlemen."

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

Ds

-0.79

osta

-0.70

yrus

-0.68

onis

-0.68

aya

-0.67

ython

-0.67

icted

-0.66

Emb

-0.65

sequence

-0.65

aeda

-0.65

POSITIVE LOGITS

 gentlemen

0.89

maid

0.85

 gentleman

0.83

utenant

0.77

men

0.75

woman

0.75

owship

0.75

 Gaga

0.74

bugs

0.72

 Toast

0.70

Activations Density 0.015%

terms addressing audiences in a formal setting

mentions of "ladies" and "gentlemen."

No Comments

No Known Activations