INDEX

Explanations

phrases describing hidden agendas or deceptive actions

oai_token-act-pair · gpt-3.5-turbo

instances of deceptive language or misrepresentation

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

Sob

-0.66

chenko

-0.62

gra

-0.61

bent

-0.60

loads

-0.60

 Survey

-0.59

ozy

-0.59

cedes

-0.58

below

-0.58

 polled

-0.58

POSITIVE LOGITS

 innocuous

0.92

 invincible

0.79

 innocence

0.78

OPA

0.76

UL

0.74

 benign

0.72

 harmless

0.66

rud

0.63

 neutrality

0.62

regn

0.61

Activations Density 0.741%

phrases describing hidden agendas or deceptive actions

instances of deceptive language or misrepresentation

No Comments

No Known Activations