INDEX

Explanations

proper nouns, specifically related to the name "Barbara"

oai_token-act-pair · gpt-3.5-turbo

the name "Barbara" in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

mble

-0.94

ngth

-0.89

byter

-0.85

olulu

-0.77

worldly

-0.76

²¾

-0.75

fecture

-0.72

ebus

-0.71

yrim

-0.71

itialized

-0.69

POSITIVE LOGITS

 Walters

1.05

 Barbara

0.87

 Hamb

0.85

 Blossom

0.78

anca

0.78

Eh

0.75

 Levy

0.75

Wid

0.74

 Gordon

0.72

 Garrison

0.71

Activations Density 0.008%

proper nouns, specifically related to the name "Barbara"

the name "Barbara" in various contexts

No Comments

No Known Activations