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

hyde

-0.97

UX

-0.75

onge

-0.74

ividual

-0.70

auga

-0.68

iless

-0.67

uty

-0.66

velop

-0.64

ricular

-0.62

cean

-0.62

POSITIVE LOGITS

yards

0.69

inates

0.69

Nat

0.65

reciation

0.65

Hung

0.62

roads

0.61

Georg

0.61

 Bundes

0.59

 False

0.59

fired

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.