INDEX

Explanations

violent or aggressive actions or intentions

oai_token-act-pair · gpt-3.5-turbo

actions related to punishment and control

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

ItemTracker

-0.57

Downloadha

-0.56

ãĤ´ãĥ³

-0.55

dating

-0.53

 dotted

-0.53

nih

-0.52

Nos

-0.51

 fashioned

-0.50

arij

-0.50

ebook

-0.49

POSITIVE LOGITS

uate

0.80

ISE

0.63

enance

0.62

ulate

0.59

 them

0.58

itate

0.58

him

0.58

igate

0.58

 oneself

0.55

 RELEASE

0.55

Activations Density 0.660%

violent or aggressive actions or intentions

actions related to punishment and control

No Comments

No Known Activations