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

inker

-0.68

å§«

-0.67

race

-0.67

Style

-0.65

van

-0.65

ournament

-0.65

oop

-0.65

ival

-0.64

rac

-0.64

EVA

-0.64

POSITIVE LOGITS

 Reaper

0.73

ppm

0.72

 tenth

0.65

 nearest

0.65

iferation

0.62

cially

0.62

FT

0.61

psons

0.61

anchester

0.59

Tot

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.