INDEX

Explanations

phrases highlighting positive aspects or characteristics

oai_token-act-pair · gpt-3.5-turbo

phrases that emphasize a positive sentiment or commentary about various subjects

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

à¥

-0.79

------------------------

-0.73

KO

-0.71

Lens

-0.70

OGR

-0.70

ÂłÂłÂłÂł

-0.67

âĸĳ

-0.67

âķĲâķĲ

-0.66

chen

-0.65

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

-0.65

POSITIVE LOGITS

lihood

0.83

aleb

0.70

 halfway

0.67

 airplanes

0.67

avorite

0.67

 bullets

0.65

 simultane

0.64

Nug

0.63

dinand

0.62

 transformations

0.62

Activations Density 0.067%

phrases highlighting positive aspects or characteristics

phrases that emphasize a positive sentiment or commentary about various subjects

No Comments

No Known Activations