INDEX

Explanations

proper nouns or names

oai_token-act-pair · gpt-3.5-turbo

references to specific names or titles associated with various groups or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

-0.71

cens

-0.65

credit

-0.61

ãĥķãĤ¡

-0.60

âĢ

-0.60

_-_

-0.58

::::::::

-0.58

():

-0.57

ionage

-0.57

 SIGN

-0.56

POSITIVE LOGITS

hovah

0.84

 Moroc

0.81

ĪĴ

0.79

senal

0.73

 exting

0.71

yang

0.70

¥ŀ

0.67

sterdam

0.67

srf

0.66

 councill

0.65

Activations Density 0.506%

proper nouns or names

references to specific names or titles associated with various groups or entities

No Comments

No Known Activations