INDEX

Explanations

the word "man" in various contexts

oai_token-act-pair · gpt-3.5-turbo

references to "man" and related expressions of masculinity

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

ADRA

-0.73

LCS

-0.73

PsyNetMessage

-0.71

Democratic

-0.69

RIPT

-0.68

ython

-0.67

 Cosponsors

-0.67

IFT

-0.65

Detroit

-0.63

REDACTED

-0.62

POSITIVE LOGITS

ifest

1.13

hunt

1.07

hood

1.06

fred

1.02

gling

0.99

hattan

0.98

agers

0.95

liness

0.93

oeuv

0.92

uscript

0.92

Activations Density 0.061%

the word "man" in various contexts

references to "man" and related expressions of masculinity

No Comments

No Known Activations