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

cks

-0.75

oan

-0.74

levels

-0.72

eme

-0.71

sold

-0.71

rick

-0.70

birth

-0.70

lets

-0.70

igm

-0.69

umen

-0.69

POSITIVE LOGITS

KEN

0.73

 Removal

0.71

 Corps

0.67

 Electoral

0.65

 Effective

0.64

 fixme

0.63

 Seym

0.62

 Flask

0.61

 Wilderness

0.61

 Volunte

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.