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

wcs

-0.71

 "$:/

-0.70

wide

-0.68

stead

-0.65

romy

-0.65

Winged

-0.64

Gall

-0.64

 reciproc

-0.63

Gry

-0.62

awaru

-0.62

POSITIVE LOGITS

ouls

0.71

=-=-

0.71

escription

0.69

IUM

0.68

 Mehran

0.67

uca

0.66

angers

0.66

osate

0.64

uminati

0.64

ilet

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.