INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ãĥĩãĤ£

-0.88

ysis

-0.77

 Tradable

-0.76

ãĤ·ãĥ£

-0.71

ãĤµ

-0.71

_-

-0.70

Xer

-0.70

tesy

-0.67

ãĤ¢ãĥ«

-0.67

ãĥĺãĥ©

-0.66

POSITIVE LOGITS

 synerg

0.74

kees

0.73

accompan

0.73

lin

0.72

akin

0.70

asonic

0.69

 millenn

0.68

tho

0.68

 strat

0.68

cano

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.