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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

phia

-0.74

lif

-0.69

vere

-0.68

 Cann

-0.65

 ancest

-0.60

 alle

-0.59

PB

-0.58

 Doctrine

-0.58

BEL

-0.58

EUR

-0.57

POSITIVE LOGITS

oint

0.84

UI

0.79

TPPStreamerBot

0.79

Alert

0.71

iatrics

0.69

autions

0.65

sheet

0.63

auldron

0.63

 fundament

0.62

abal

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.