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

alysed

-0.71

 disappro

-0.66

ARB

-0.65

º

-0.62

tics

-0.61

raid

-0.61

ĨĴ

-0.60

 Shutterstock

-0.59

olds

-0.59

PAR

-0.59

POSITIVE LOGITS

usha

0.71

gers

0.67

gen

0.67

tool

0.67

mess

0.66

Mess

0.66

edition

0.66

Club

0.64

gone

0.63

anian

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.