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

adem

-0.79

inth

-0.75

uscript

-0.74

itals

-0.72

efficients

-0.71

ateurs

-0.68

alions

-0.68

lean

-0.68

bleacher

-0.67

Reviewer

-0.66

POSITIVE LOGITS

 Gork

0.69

obic

0.68

 Warranty

0.66

ISE

0.65

NX

0.62

ETA

0.58

 baggage

0.58

ãĥ©ãĥ³

0.57

UTC

0.57

IME

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.