INDEX

Explanations

words related to criticism or judgment

oai_token-act-pair · gpt-3.5-turbo

forms of the verb "to be."

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

è¦ļéĨĴ

-0.70

 Buff

-0.69

ãĥĥãĥĪ

-0.64

ATK

-0.62

ASC

-0.61

spo

-0.60

kW

-0.60

 spoiler

-0.59

 gradient

-0.58

 integral

-0.58

POSITIVE LOGITS

itivity

1.03

hement

0.97

itiveness

0.94

uries

0.90

estyles

0.89

pec

0.88

metics

0.88

ciation

0.87

eline

0.87

terness

0.86

Activations Density 0.055%

words related to criticism or judgment

forms of the verb "to be."

No Comments

No Known Activations