INDEX

Explanations

mentions of the word "Poison" and related terms

oai_token-act-pair · gpt-3.5-turbo

terms related to poisoning and toxic substances

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

astical

-0.87

astically

-0.84

ulative

-0.80

blance

-0.79

tac

-0.76

undo

-0.71

appers

-0.70

ifter

-0.69

astics

-0.69

onductor

-0.69

POSITIVE LOGITS

ously

0.97

nect

0.97

ition

0.95

ous

0.93

essee

0.83

naires

0.82

vironment

0.82

 Wonderland

0.81

Ivy

0.81

naire

0.79

Activations Density 0.076%

mentions of the word "Poison" and related terms

terms related to poisoning and toxic substances

No Comments

No Known Activations