INDEX

Explanations

mentions of tampering or manipulation

oai_token-act-pair · gpt-3.5-turbo

references to tampering and related activities

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

anamo

-0.80

ilipp

-0.72

BuyableInstoreAndOnline

-0.71

zl

-0.69

 Sigma

-0.68

sam

-0.68

RIC

-0.65

AIN

-0.65

hens

-0.65

auri

-0.64

POSITIVE LOGITS

 tampering

0.99

tam

0.94

 tink

0.80

ritten

0.79

etry

0.77

rodu

0.75

bley

0.72

aker

0.68

 havoc

0.68

ington

0.67

Activations Density 0.041%

mentions of tampering or manipulation

references to tampering and related activities

No Comments

No Known Activations