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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 constit

-0.73

 intervening

-0.72

kees

-0.67

 manned

-0.66

geries

-0.65

 fielding

-0.64

 welf

-0.64

ocratic

-0.62

 framing

-0.62

 permitting

-0.61

POSITIVE LOGITS

 Dimension

0.83

 Underground

0.73

cation

0.73

 Ratings

0.72

REF

0.68

IFIC

0.68

 Lethal

0.67

Country

0.66

 Sunset

0.66

 Piper

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.