INDEX

Explanations

patents and technical terms

oai_token-act-pair · gpt-3.5-turbo

abbreviations and acronyms related to the United States

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

axter

-0.74

*/(

-0.71

 srfAttach

-0.69

ï¸ı

-0.68

stroke

-0.63

 bleach

-0.63

cells

-0.63

 brim

-0.62

roxy

-0.60

SourceFile

-0.59

POSITIVE LOGITS

ciating

0.70

psons

0.69

æĸ¹

0.68

å£«

0.68

uthor

0.67

EMENT

0.66

REAM

0.66

itary

0.66

ili

0.65

DIR

0.64

Activations Density 0.169%

patents and technical terms

abbreviations and acronyms related to the United States

No Comments

No Known Activations