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

IBLE

-0.65

 Ragnarok

-0.60

NER

-0.59

strap

-0.58

ica

-0.58

 Nether

-0.58

racuse

-0.57

 Horizon

-0.57

 socket

-0.57

 Jensen

-0.57

POSITIVE LOGITS

Merit

0.83

 enthusi

0.80

ĪĴ

0.75

yss

0.70

 antid

0.70

Args

0.65

alsa

0.65

ADRA

0.64

Newsletter

0.63

Ĥª

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.