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

escape

-0.87

agate

-0.79

Asia

-0.75

 Gong

-0.73

 Overwatch

-0.73

Ev

-0.72

Fast

-0.72

uper

-0.71

£

-0.70

Lei

-0.70

POSITIVE LOGITS

 bree

0.74

 cartoons

0.73

 maple

0.73

 strands

0.71

mus

0.70

 crochet

0.68

 appl

0.67

 sock

0.66

 latex

0.64

 veins

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.