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

erness

-0.70

heid

-0.66

atform

-0.66

NESS

-0.66

terday

-0.65

vana

-0.64

 Superior

-0.63

igi

-0.62

MV

-0.61

winner

-0.60

POSITIVE LOGITS

Snake

0.72

ãĥīãĥ©

0.70

 REPORT

0.64

 faked

0.62

 Surve

0.60

isons

0.60

Reviewed

0.59

Saudi

0.59

pring

0.59

reve

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.