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

isu

-0.74

imi

-0.69

bay

-0.66

 Mariners

-0.63

 Sens

-0.62

âĢ¢âĢ¢

-0.62

jon

-0.62

NRS

-0.61

 Rays

-0.60

rations

-0.58

POSITIVE LOGITS

FORE

0.78

uthor

0.68

IFT

0.68

OPA

0.66

 independence

0.65

ACY

0.63

MODE

0.62

dl

0.62

isoft

0.62

 handlers

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.