INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

fal

-0.72

olo

-0.68

udic

-0.68

icz

-0.66

elson

-0.65

iger

-0.65

ibaba

-0.64

efficients

-0.64

atural

-0.64

yth

-0.63

POSITIVE LOGITS

0000000000000000

0.60

rator

0.60

++;

0.60

$.

0.60

IRO

0.59

×Ļ

0.58

eki

0.57

 clar

0.57

nai

0.57

OTH

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.