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

FTWARE

-0.79

 Grounds

-0.69

wcs

-0.62

BF

-0.61

adra

-0.60

 Lime

-0.59

Cas

-0.59

atform

-0.58

mosp

-0.58

Ame

-0.58

POSITIVE LOGITS

raid

0.68

enable

0.63

baby

0.61

 insecurity

0.61

 reluct

0.60

 Paramount

0.59

vid

0.59

 allergy

0.59

antry

0.58

indu

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.