INDEX

Explanations

mentions of or references to harm or potential harm

oai_token-act-pair · gpt-3.5-turbo

references to harm or injury

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

KER

-0.72

zsche

-0.71

 liner

-0.70

ARCH

-0.68

ulators

-0.65

ipel

-0.65

ulating

-0.62

ulous

-0.62

uration

-0.62

 Currency

-0.61

POSITIVE LOGITS

onies

1.27

lessly

1.26

fully

0.98

 inflicted

0.96

ful

0.92

 harm

0.89

lessness

0.89

fulness

0.88

bringer

0.85

 harms

0.81

Activations Density 0.029%

mentions of or references to harm or potential harm

references to harm or injury

No Comments

No Known Activations