INDEX

Explanations

proper nouns, particularly names of individuals

oai_token-act-pair · gpt-3.5-turbo

phrases indicating membership or inclusion in a group

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

bis

-0.94

ramid

-0.84

ahime

-0.84

iosity

-0.72

lag

-0.70

 guiActiveUnfocused

-0.70

nosis

-0.68

ens

-0.66

 simulac

-0.66

fal

-0.66

POSITIVE LOGITS

 former

1.11

 Mohamed

1.03

Abd

1.01

 longtime

1.00

 representatives

1.00

 Reps

0.99

 Pamela

0.98

 Christine

0.98

Lt

0.97

 Denis

0.97

Activations Density 0.277%

proper nouns, particularly names of individuals

phrases indicating membership or inclusion in a group

No Comments

No Known Activations