INDEX

Explanations

names of individuals or entities

oai_token-act-pair · gpt-3.5-turbo

proper nouns, specifically names and geographical locations

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

 shareholder

-0.63

 diligence

-0.63

 footprints

-0.60

²¾

-0.60

 prosecut

-0.57

 watt

-0.57

 ticking

-0.57

olitics

-0.57

 whisper

-0.55

 shareholders

-0.55

POSITIVE LOGITS

quartered

0.81

quart

0.79

pai

0.78

osterone

0.78

llor

0.74

bia

0.74

iard

0.71

aghd

0.70

christ

0.69

elaide

0.69

Activations Density 0.272%

names of individuals or entities

proper nouns, specifically names and geographical locations

No Comments

No Known Activations