INDEX

Explanations

proper nouns related to individuals

oai_token-act-pair · gpt-3.5-turbo

instances of the letter 'g'

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

Negative Logits

 compr

-0.71

 psychiat

-0.69

 mosqu

-0.64

 scrut

-0.61

ĸļ

-0.61

 Progressive

-0.61

 Lauder

-0.61

CBO

-0.61

 derail

-0.60

©¶æ¥µ

-0.60

POSITIVE LOGITS

uild

1.26

reens

1.16

raphics

1.15

raphic

1.13

endered

1.07

raham

1.07

ossip

1.06

arden

1.04

hetto

1.03

ospel

1.02

Activations Density 0.044%

proper nouns related to individuals

instances of the letter 'g'

No Known Activations