INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

 Spoiler

-0.71

 Survive

-0.65

eric

-0.65

SUR

-0.64

 Profit

-0.63

RAG

-0.62

Answer

-0.61

 rage

-0.59

 Aware

-0.59

 Copy

-0.59

POSITIVE LOGITS

bilt

0.90

cham

0.81

 Palest

0.79

tob

0.74

 suspic

0.70

cyl

0.68

assian

0.68

 Mutant

0.67

 corrid

0.67

 mosqu

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.