INDEX

Explanations

references to robots and pop culture such as movies, celebrities, and books

oai_token-act-pair · gpt-3.5-turbo

references to robots and notable personalities in popular culture

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ksh

-0.85

clair

-0.77

ardless

-0.70

ulhu

-0.69

sburg

-0.68

iries

-0.67

okane

-0.67

verson

-0.67

ppe

-0.66

wait

-0.66

POSITIVE LOGITS

 Robot

1.02

nik

0.90

 Racer

0.87

MpServer

0.84

Eye

0.80

Series

0.79

tek

0.79

Network

0.77

 Fighters

0.75

Rocket

0.75

Activations Density 0.018%

references to robots and pop culture such as movies, celebrities, and books

references to robots and notable personalities in popular culture

No Comments

No Known Activations