INDEX

Explanations

the word "bon" with varying activation levels

oai_token-act-pair · gpt-3.5-turbo

the term "bon" and its various contexts

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

 Administ

-0.90

TY

-0.73

REAM

-0.69

ECT

-0.68

 Proposition

-0.67

 Clin

-0.65

AY

-0.65

natureconservancy

-0.65

ORT

-0.64

APS

-0.62

POSITIVE LOGITS

bon

1.44

etooth

1.05

neau

1.03

ilib

0.90

otaur

0.88

bons

0.88

fman

0.86

uses

0.86

amic

0.83

wich

0.83

Activations Density 0.004%

the word "bon" with varying activation levels

the term "bon" and its various contexts

No Comments

No Known Activations