INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

ESV

-0.69

iveness

-0.68

irc

-0.64

manship

-0.63

efficients

-0.61

UTC

-0.61

 Average

-0.60

 Amount

-0.59

([

-0.58

ework

-0.58

POSITIVE LOGITS

 hesitate

0.76

 unpre

0.72

 flush

0.68

itially

0.68

uez

0.67

gat

0.65

allery

0.65

 opting

0.64

oslov

0.63

shy

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.