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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Swords

-0.77

 Chronicles

-0.75

Tree

-0.73

 Bonds

-0.65

 Tree

-0.65

Yon

-0.64

 Trees

-0.64

 Exile

-0.63

 Bullet

-0.61

 Trails

-0.61

POSITIVE LOGITS

chance

0.74

iculty

0.74

aution

0.74

try

0.72

ĳå£«

0.69

 confuse

0.67

erest

0.66

 dign

0.65

priv

0.63

 inconvenience

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.