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

utterstock

-0.80

ĸļ

-0.79

uter

-0.71

\":

-0.71

tin

-0.68

ettings

-0.67

 Abedin

-0.66

ittal

-0.65

roup

-0.65

rea

-0.65

POSITIVE LOGITS

 synerg

0.71

 Fang

0.68

 Angry

0.58

 Towers

0.58

 assail

0.57

 Shroud

0.57

 provoke

0.57

 strike

0.56

 deserve

0.56

Bull

0.55

Activations Density 0.000%

No Known Activations

This feature has no known activations.