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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æĺ¯

-0.70

icro

-0.68

SOURCE

-0.67

 Latter

-0.67

Contribut

-0.64

efer

-0.63

orest

-0.63

iuses

-0.62

 Fool

-0.62

 billionaires

-0.61

POSITIVE LOGITS

 puberty

0.73

uries

0.70

 rehe

0.67

esthesia

0.67

reath

0.67

une

0.65

rea

0.65

hern

0.64

wana

0.62

arette

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.