INDEX

Explanations

references to physically using hands in various activities

oai_token-act-pair · gpt-3.5-turbo

phrases related to obtaining or controlling something

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

ļéĨĴ

-0.74

ITAL

-0.65

 Allies

-0.62

athan

-0.61

ansion

-0.61

rious

-0.60

Marginal

-0.60

 RAND

-0.60

vation

-0.60

POSITIVE LOGITS

pring

1.16

creen

1.04

maid

1.02

bag

0.90

ets

0.89

handed

0.89

picked

0.87

chool

0.87

shake

0.87

ingers

0.87

Activations Density 0.024%

references to physically using hands in various activities

phrases related to obtaining or controlling something

No Comments

No Known Activations