INDEX

Explanations

proper nouns, particularly the name "Robin"

oai_token-act-pair · gpt-3.5-turbo

occurrences of the name "Robin."

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

mble

-0.92

ormons

-0.76

ntil

-0.75

resso

-0.73

aternity

-0.71

ller

-0.70

gerald

-0.70

bye

-0.70

chnology

-0.70

ccording

-0.69

POSITIVE LOGITS

 Hood

1.23

 Robin

0.98

ette

0.91

Robin

0.87

 Williams

0.79

 Mans

0.78

 Lopez

0.78

 Oliver

0.77

otte

0.75

 Bean

0.75

Activations Density 0.006%

proper nouns, particularly the name "Robin"

occurrences of the name "Robin."

No Comments

No Known Activations