INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

owder

-0.77

achy

-0.75

iors

-0.75

itia

-0.74

aucus

-0.68

umbnails

-0.66

 Mustang

-0.66

phia

-0.66

 RCMP

-0.66

nsics

-0.66

POSITIVE LOGITS

 multiplier

0.75

etheless

0.71

0.70

ptin

0.69

 disl

0.68

multipl

0.67

è¦ļéĨĴ

0.66

 stakes

0.64

 extr

0.64

cyt

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.