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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ãĥĻ

-0.84

nings

-0.77

oslav

-0.65

IFF

-0.65

Fi

-0.65

 Telescope

-0.64

bright

-0.63

 Angels

-0.62

inators

-0.62

éģ

-0.62

POSITIVE LOGITS

ysc

0.70

 ende

0.64

paio

0.63

proxy

0.63

cffffcc

0.63

 breaths

0.63

insky

0.61

 tremend

0.61

alus

0.60

 disse

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.