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

ahime

-0.77

lay

-0.75

liest

-0.74

lance

-0.72

lier

-0.69

affer

-0.68

estine

-0.64

rab

-0.64

rats

-0.62

tesy

-0.61

POSITIVE LOGITS

 Nadu

0.82

ental

0.69

 habitual

0.68

ADS

0.66

INGTON

0.62

Origin

0.61

 veget

0.61

 Digest

0.61

ãģį

0.60

 Vital

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.