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

aughs

-0.77

 arms

-0.75

 grips

-0.74

 latex

-0.73

 Ashton

-0.72

Lis

-0.69

 Celt

-0.69

apons

-0.67

 Portug

-0.67

 Guer

-0.66

POSITIVE LOGITS

cool

0.90

fun

0.87

no

0.86

few

0.84

don

0.84

just

0.84

whe

0.81

ev

0.78

yet

0.76

altern

0.75

Activations Density 0.000%

No Known Activations

This feature has no known activations.