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

ãĥ¼ãĥĨãĤ£

-0.76

 Flavoring

-0.75

ãĥ¯

-0.72

 Siberia

-0.71

 Divide

-0.71

bos

-0.70

 Gleaming

-0.69

 Nare

-0.68

bler

-0.66

Sao

-0.65

POSITIVE LOGITS

olar

0.93

rent

0.85

otto

0.79

onder

0.78

brance

0.76

onne

0.76

pport

0.76

nery

0.72

pires

0.72

iques

0.71

Activations Density 0.000%

No Known Activations

This feature has no known activations.