INDEX

Explanations

proper nouns or phrases related to specific places, organizations, or people

oai_token-act-pair · gpt-3.5-turbo

terms related to gaming and significant negative actions or events

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 Palest

-0.69

 fluor

-0.66

 vouchers

-0.65

EStream

-0.64

TAM

-0.62

 boycot

-0.61

 expend

-0.57

 Charlottesville

-0.56

 Rico

-0.56

 isol

-0.55

POSITIVE LOGITS

opsis

0.67

ean

0.66

 Brothers

0.65

itty

0.65

ake

0.65

sounding

0.65

brew

0.63

utions

0.62

ilib

0.62

oot

0.62

Activations Density 0.369%

proper nouns or phrases related to specific places, organizations, or people

terms related to gaming and significant negative actions or events

No Comments

No Known Activations