INDEX

Explanations

numbers with decimal points indicating sizes or measurements

oai_token-act-pair · gpt-3.5-turbo

numerical data and statistics

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

schild

-0.86

ouver

-0.79

owship

-0.76

ulkan

-0.74

enhagen

-0.71

ynt

-0.67

 opposing

-0.66

mouse

-0.66

culosis

-0.64

pees

-0.64

POSITIVE LOGITS

ĨĴ

0.69

©¶æ

0.68

 Centauri

0.67

 Siren

0.66

GHz

0.65

thood

0.62

fter

0.62

ually

0.60

GHz

0.59

ctory

0.59

Activations Density 0.196%

numbers with decimal points indicating sizes or measurements

numerical data and statistics

No Comments

No Known Activations