INDEX

Explanations

names or terms related to a specific individual or entity

oai_token-act-pair · gpt-3.5-turbo

mentions of specific names or terms related to individuals or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Hew

-0.72

 Veronica

-0.67

 Mess

-0.67

 Commodore

-0.66

OCD

-0.66

 Wonderland

-0.64

 Visual

-0.62

 Winning

-0.60

 Kitty

-0.60

EN

-0.60

POSITIVE LOGITS

arb

4.74

arak

1.75

arbon

1.55

bard

1.44

adish

1.44

ARB

1.14

atel

1.09

aram

1.07

elta

1.04

kef

1.04

Activations Density 0.028%

names or terms related to a specific individual or entity

mentions of specific names or terms related to individuals or entities

No Comments

No Known Activations