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

 sugg

-0.67

 relapse

-0.64

 buckle

-0.64

 tariff

-0.63

 Carbuncle

-0.63

 blight

-0.61

 Fever

-0.61

 outward

-0.60

 lent

-0.59

 itch

-0.59

POSITIVE LOGITS

Kru

0.79

adr

0.75

yss

0.75

sonian

0.74

ovo

0.72

lly

0.72

gon

0.70

USE

0.69

rax

0.69

irds

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.