INDEX

Explanations

phrases related to policy and government actions

oai_token-act-pair · gpt-3.5-turbo

phrases related to safety and well-being

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

 confir

-0.70

 ende

-0.70

 misunder

-0.65

 dismant

-0.62

 destro

-0.62

 Learns

-0.59

OSP

-0.59

ather

-0.59

 Rampage

-0.58

 reluct

-0.58

POSITIVE LOGITS

ibel

0.63

into

0.62

 innocent

0.61

oths

0.58

Inn

0.58

evil

0.56

rum

0.56

 Narr

0.56

rily

0.55

metadata

0.55

Activations Density 0.767%

phrases related to policy and government actions

phrases related to safety and well-being

No Comments

No Known Activations