INDEX

Explanations

terms related to categorization or classification

oai_token-act-pair · gpt-3.5-turbo

references to specific categories or classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.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.5.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

bats

-0.81

 Zimmer

-0.77

RIS

-0.72

 ultras

-0.66

gotten

-0.61

kj

-0.59

 Trojan

-0.58

Rez

-0.58

 Tycoon

-0.58

 Lans

-0.58

POSITIVE LOGITS

naire

0.95

category

0.88

oola

0.80

ifier

0.80

rss

0.79

bars

0.78

omial

0.78

 categories

0.78

Category

0.77

wagon

0.77

Activations Density 0.016%

terms related to categorization or classification

references to specific categories or classifications

No Comments

No Known Activations