INDEX

Explanations

names related to military figures or characters

oai_token-act-pair · gpt-3.5-turbo

names of places and characters associated with a particular narrative or context

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

nect

-0.90

peat

-0.72

 overboard

-0.72

washing

-0.70

ciples

-0.68

figure

-0.65

joice

-0.64

issance

-0.64

natureconservancy

-0.64

merce

-0.64

POSITIVE LOGITS

inia

1.05

inus

0.90

0.84

inian

0.80

iem

0.80

ĳå£«

0.79

andr

0.79

pheus

0.77

ername

0.76

 mund

0.74

Activations Density 0.140%

names related to military figures or characters

names of places and characters associated with a particular narrative or context

No Comments

No Known Activations