INDEX

Explanations

instances of the word "Bon" followed by a number, potentially related to a person's name or a specific keyword

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Bon."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

dfx

-0.88

ELD

-0.72

gamer

-0.69

UGE

-0.69

INAL

-0.68

 Editorial

-0.66

 Ethics

-0.66

ODE

-0.66

Snake

-0.62

Ire

-0.62

POSITIVE LOGITS

anza

1.06

iton

1.01

gey

0.98

uses

0.97

illas

0.93

Bon

0.91

itors

0.91

izons

0.90

neau

0.89

anz

0.89

Activations Density 0.011%

instances of the word "Bon" followed by a number, potentially related to a person's name or a specific keyword

mentions of the name "Bon."

No Comments

No Known Activations