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

CRE

-0.68

 Moor

-0.66

PLIED

-0.65

ORPG

-0.65

 Corsair

-0.65

SELECT

-0.63

-0.62

+(

-0.62

PO

-0.62

Pool

-0.61

POSITIVE LOGITS

zzle

0.93

eph

0.78

heed

0.73

pees

0.69

inous

0.69

riage

0.69

 rollout

0.68

 firmware

0.68

ptions

0.67

mits

0.67

Activations Density 0.000%

No Known Activations

This feature has no known activations.