INDEX

Explanations

proper nouns and specific terms related to various entities or organizations

oai_token-act-pair · gpt-3.5-turbo

proper nouns or specific entities

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

åĤ

-0.79

cffff

-0.76

insula

-0.74

uminati

-0.67

 womb

-0.65

chest

-0.64

lihood

-0.64

*.

-0.63

abwe

-0.62

mble

-0.62

POSITIVE LOGITS

 Sand

0.71

 backers

0.64

lett

0.61

 Hacker

0.60

Boo

0.59

mania

0.59

Sand

0.59

Taj

0.59

 programmers

0.58

Hag

0.58

Activations Density 0.578%

proper nouns and specific terms related to various entities or organizations

proper nouns or specific entities

No Comments

No Known Activations