INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

cffff

-0.73

 Derby

-0.69

 Hoover

-0.69

bub

-0.66

Rich

-0.66

 conce

-0.63

 watered

-0.62

keley

-0.61

 indo

-0.60

odox

-0.60

POSITIVE LOGITS

ãĥīãĥ©ãĤ´ãĥ³

0.83

sts

0.77

interstitial

0.67

cific

0.67

tenance

0.66

hern

0.66

tical

0.65

ãĥł

0.65

TN

0.65

ãģį

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.