INDEX

Explanations

phrases describing highly skilled individuals

oai_token-act-pair · gpt-3.5-turbo

references to talent or skilled individuals

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

ptions

-0.81

ocene

-0.72

thur

-0.70

phrine

-0.70

oths

-0.68

FACE

-0.66

cise

-0.66

cott

-0.66

 abolished

-0.64

emb

-0.64

POSITIVE LOGITS

 talents

0.99

 talent

0.90

 minds

0.86

ness

0.86

 enough

0.82

 artist

0.78

 pian

0.78

heet

0.78

 young

0.77

 entreprene

0.76

Activations Density 0.029%

phrases describing highly skilled individuals

references to talent or skilled individuals

No Comments

No Known Activations