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

leans

-0.70

emic

-0.70

 improv

-0.67

 mobilization

-0.67

ishing

-0.65

è¯

-0.61

 twists

-0.61

 submer

-0.61

overed

-0.59

 redes

-0.59

POSITIVE LOGITS

":["

0.80

LEASE

0.78

Ice

0.77

NOW

0.76

":[{"

0.71

ENA

0.71

hof

0.71

Diamond

0.70

ucket

0.69

WF

0.69

Activations Density 0.000%

No Known Activations

This feature has no known activations.