INDEX

Explanations

phrases or names related to individuals

oai_token-act-pair · gpt-3.5-turbo

names of people or entities, particularly in a publishing context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 7-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.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

 Akin

-0.73

ascript

-0.66

 adolesc

-0.65

 pains

-0.65

 mornings

-0.60

olor

-0.60

abase

-0.60

itably

-0.60

 acquisitions

-0.58

 deceptive

-0.58

POSITIVE LOGITS

ophy

0.79

kov

0.66

aviour

0.65

iazep

0.64

Ĥ¬

0.64

pad

0.64

oshenko

0.64

drm

0.62

zag

0.61

ç«

0.61

Activations Density 0.204%

phrases or names related to individuals

names of people or entities, particularly in a publishing context

No Comments

No Known Activations