INDEX

Explanations

names of individuals

oai_token-act-pair · gpt-3.5-turbo

proper nouns, particularly names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

PDATE

-0.84

cffff

-0.83

technical

-0.75

direction

-0.75

querque

-0.75

ints

-0.72

nown

-0.72

ozy

-0.71

riter

-0.71

taboola

-0.71

POSITIVE LOGITS

 Marie

1.30

 Lynn

1.22

Mae

1.21

 Louise

1.20

 Anne

1.20

Anne

1.18

 Nicole

1.16

 herself

1.14

Marie

1.13

Rae

1.05

Activations Density 0.279%

names of individuals

proper nouns, particularly names

No Comments

No Known Activations