INDEX

Explanations

pronouns referring to males, particularly starting with the word "he"

oai_token-act-pair · gpt-3.5-turbo

references to a male individual

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

 Seym

-0.72

emale

-0.70

etheless

-0.66

raints

-0.57

igslist

-0.57

flix

-0.56

 constit

-0.55

terms

-0.54

deen

-0.52

execute

-0.52

POSITIVE LOGITS

zbollah

0.91

mos

0.77

 Majesty

0.75

eded

0.73

sych

0.67

dor

0.66

brew

0.65

sing

0.65

'd

0.64

ALTH

0.64

Activations Density 0.252%

pronouns referring to males, particularly starting with the word "he"

references to a male individual

No Comments

No Known Activations