INDEX

Explanations

pronouns that refer to "he" or "she" at high activation levels

oai_token-act-pair · gpt-3.5-turbo

references to gender pronouns, specifically "he" and "she."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

Joy

-0.85

 Vive

-0.71

Dam

-0.70

rar

-0.69

Sov

-0.66

Vil

-0.65

 Cruiser

-0.65

Js

-0.64

 Squid

-0.63

POSITIVE LOGITS

itage

0.75

self

0.73

own

0.71

ãĤ´ãĥ³

0.71

 initials

0.71

itant

0.67

gdala

0.66

agher

0.64

owe

0.64

 fate

0.63

Activations Density 0.058%

pronouns that refer to "he" or "she" at high activation levels

references to gender pronouns, specifically "he" and "she."

No Comments

No Known Activations