INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

gery

-0.75

Interstitial

-0.73

ued

-0.71

asca

-0.70

nir

-0.69

dq

-0.68

elsius

-0.68

limit

-0.67

leneck

-0.66

illin

-0.66

POSITIVE LOGITS

hess

0.67

 PLAY

0.65

 VIDE

0.64

ÃįÃį

0.62

 reverber

0.62

 play

0.61

ELE

0.60

ESV

0.60

eger

0.59

 simul

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.