INDEX

Explanations

terms relating to variations or distinctions between groups or individuals

oai_token-act-pair · gpt-3.5-turbo

the concept of differences across various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rollers

-0.82

ãĥİ

-0.75

tsky

-0.71

×Ķ

-0.69

roller

-0.68

ergy

-0.67

gary

-0.66

ATA

-0.65

ODE

-0.64

DA

-0.64

POSITIVE LOGITS

yip

0.99

iating

0.91

iveness

0.90

ials

0.84

 between

0.84

ļéĨĴ

0.82

inctions

0.80

aroo

0.79

 citiz

0.78

iator

0.78

Activations Density 0.024%

terms relating to variations or distinctions between groups or individuals

the concept of differences across various contexts

No Comments

No Known Activations