INDEX

Explanations

the word "lad" at varying levels of activation

oai_token-act-pair · gpt-3.5-turbo

the term "lad" and its variations, suggesting a focus on youth or male identity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

HOME

-0.78

anwhile

-0.76

PRES

-0.74

PORT

-0.70

KN

-0.70

ãģķ

-0.69

peace

-0.69

 Personality

-0.68

=#

-0.68

 FISA

-0.65

POSITIVE LOGITS

lad

1.05

sheets

0.96

sheet

0.87

itionally

0.86

enance

0.86

ening

0.86

ys

0.86

bags

0.84

books

0.82

loads

0.82

Activations Density 0.009%

the word "lad" at varying levels of activation

the term "lad" and its variations, suggesting a focus on youth or male identity

No Comments

No Known Activations