INDEX

Explanations

references to specific locations or entities

oai_token-act-pair · gpt-3.5-turbo

references to governments, military entities, and political structures

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 9-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.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

Ô

-0.97

ãĤ¡

-0.72

iHUD

-0.72

 Last

-0.64

 Remix

-0.64

thood

-0.64

stasy

-0.63

Minecraft

-0.62

phies

-0.62

hemy

-0.61

POSITIVE LOGITS

 authorities

1.02

 populace

1.00

 legislature

0.94

 intends

0.93

 retains

0.92

 chooses

0.90

 judiciary

0.90

 cannot

0.89

 realizes

0.89

 prefers

0.88

Activations Density 0.561%

references to specific locations or entities

references to governments, military entities, and political structures

No Comments

No Known Activations