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

 âĸº

-0.84

TAIN

-0.76

 Thumbnails

-0.72

catentry

-0.71

FTWARE

-0.71

ALT

-0.67

oyer

-0.66

à¥

-0.64

"}

-0.64

à¤¾

-0.63

POSITIVE LOGITS

ression

0.75

oha

0.75

rpm

0.64

ately

0.61

olation

0.61

sburgh

0.59

packing

0.59

ographically

0.58

 reincarn

0.58

 sidew

0.58

Activations Density 0.000%

No Known Activations

This feature has no known activations.