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

ONSORED

-0.72

hess

-0.70

efer

-0.67

âĶĢâĶĢâĶĢâĶĢ

-0.66

 Pred

-0.64

tyard

-0.64

]);

-0.63

viron

-0.60

-0.58

POSITIVE LOGITS

ysis

0.82

anski

0.69

ovember

0.68

ocally

0.67

aunders

0.66

achu

0.65

club

0.65

ItemImage

0.65

ogs

0.64

hops

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.