INDEX

Explanations

keywords related to specific objects or items

oai_token-act-pair · gpt-3.5-turbo

nouns related to various physical objects and entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

ãĤ©

-0.54

 charism

-0.52

 circumstance

-0.51

atalie

-0.51

athan

-0.48

noon

-0.46

atever

-0.44

 Huck

-0.43

rance

-0.43

 Edmund

-0.43

POSITIVE LOGITS

paces

1.16

mith

1.14

peed

1.03

pace

1.01

creen

0.98

hips

0.97

ynthesis

0.97

chool

0.94

heet

0.93

uits

0.93

Activations Density 0.745%

keywords related to specific objects or items

nouns related to various physical objects and entities

No Comments

No Known Activations