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

closure

-0.66

DAQ

-0.64

ribune

-0.62

robe

-0.62

ective

-0.61

kick

-0.60

iary

-0.60

TER

-0.60

 Quin

-0.59

vern

-0.58

POSITIVE LOGITS

hent

0.69

bh

0.68

anz

0.62

pha

0.62

 anchored

0.61

assy

0.60

eme

0.60

antz

0.59

">

0.59

 Higgins

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.