INDEX

Explanations

words related to physical descriptions like "hunched," "huddled," "hanger," "blushing," etc

oai_token-act-pair · gpt-3.5-turbo

words related to breathing or physical exertion

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

BILITIES

-0.94

tions

-0.82

CHA

-0.77

BILITY

-0.75

taboola

-0.71

Iw

-0.70

oÄŁ

-0.68

Cause

-0.68

 Cosponsors

-0.67

 Sorce

-0.65

POSITIVE LOGITS

angs

0.80

inki

0.80

ftime

0.77

awei

0.76

icultural

0.74

abee

0.73

agonal

0.71

 flock

0.70

iday

0.70

acan

0.70

Activations Density 0.075%

words related to physical descriptions like "hunched," "huddled," "hanger," "blushing," etc

words related to breathing or physical exertion

No Comments

No Known Activations