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

\"

-0.64

 knots

-0.62

 muster

-0.62

 wise

-0.61

 similarities

-0.61

 warr

-0.60

ĪĴ

-0.60

aiden

-0.57

AV

-0.57

ADV

-0.57

POSITIVE LOGITS

ulus

0.79

Shares

0.75

phasis

0.75

ishers

0.72

ÅĤ

0.71

estate

0.71

mor

0.71

pees

0.71

psons

0.71

rica

0.70

Activations Density 0.000%

No Known Activations

This feature has no known activations.