INDEX

Explanations

mentions or references to political or international relations involving the United States

oai_token-act-pair · gpt-3.5-turbo

references to the United States

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

 Madden

-0.71

 TAMADRA

-0.70

é¾įå

-0.66

 McGr

-0.66

 Mermaid

-0.66

osaurs

-0.66

 Bagg

-0.65

 shelf

-0.65

çīĪ

-0.64

 Vapor

-0.64

POSITIVE LOGITS

taboola

1.00

based

0.99

division

0.96

themed

0.95

backed

0.93

facing

0.92

interstitial

0.91

ship

0.90

dep

0.88

sized

0.86

Activations Density 0.014%

mentions or references to political or international relations involving the United States

references to the United States

No Comments

No Known Activations