INDEX

Explanations

phrases related to people's names

oai_token-act-pair · gpt-3.5-turbo

references to the name "Payne" and associated terms

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

 expend

-0.76

inations

-0.74

avorite

-0.73

 wills

-0.70

icity

-0.68

 orbital

-0.68

 warr

-0.68

ISM

-0.67

 fortun

-0.66

 assassinate

-0.65

POSITIVE LOGITS

ÅĤ

0.95

SourceFile

0.89

backer

0.86

quet

0.84

waters

0.83

manship

0.80

ippi

0.80

pee

0.75

qua

0.73

forest

0.72

Activations Density 0.041%

phrases related to people's names

references to the name "Payne" and associated terms

No Comments

No Known Activations