INDEX

Explanations

mentions of the word "Gaming" at various activation levels

oai_token-act-pair · gpt-3.5-turbo

references to gaming and related entities

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

aneously

-0.75

authent

-0.75

paralle

-0.72

esters

-0.70

notations

-0.66

alogue

-0.64

obar

-0.64

alk

-0.64

tain

-0.63

asts

-0.62

POSITIVE LOGITS

 Gaming

1.13

 Esports

0.89

Gaming

0.89

GG

0.79

 Lounge

0.78

gewater

0.78

Hai

0.76

 Strategy

0.75

[+

0.75

 Control

0.74

Activations Density 0.014%

mentions of the word "Gaming" at various activation levels

references to gaming and related entities

No Comments

No Known Activations