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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

©¶æ

-0.86

unin

-0.83

cham

-0.75

arters

-0.72

 illegitimate

-0.68

Bog

-0.68

etheless

-0.67

arden

-0.66

regon

-0.66

ahon

-0.65

POSITIVE LOGITS

 COMPLE

0.67

 intersections

0.66

OAD

0.65

 Leban

0.65

 bumps

0.64

illary

0.63

addin

0.62

icity

0.61

 HIGH

0.60

Click

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.