INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 2-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.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

 TRAN

-0.69

ulhu

-0.69

 msec

-0.67

 casualty

-0.65

 circulation

-0.63

CBI

-0.63

uddin

-0.63

 casualties

-0.61

abus

-0.60

-0.59

POSITIVE LOGITS

skirts

0.81

essen

0.76

sters

0.68

ward

0.67

encing

0.67

 Kitt

0.65

eus

0.64

fort

0.63

enn

0.62

eared

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.