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

````

-0.79

iencies

-0.75

lled

-0.74

sect

-0.74

isible

-0.74

omorphic

-0.71

uminati

-0.70

clusive

-0.68

multi

-0.67

adelphia

-0.67

POSITIVE LOGITS

————————

0.97

————

0.92

————————————————

0.81

 Rosenstein

0.81

——

0.74

Enlarge

0.70

oÄŁ

0.66

 Franken

0.66

 Jonah

0.65

 Judd

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.