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

ãĥĳ

-0.83

 beaut

-0.67

 Blessing

-0.67

Friend

-0.64

Duration

-0.61

 Perse

-0.61

 Lite

-0.61

 angels

-0.60

 Basil

-0.59

 Weasley

-0.59

POSITIVE LOGITS

culosis

0.84

irrel

0.73

 Investigative

0.72

seys

0.72

iven

0.71

ipel

0.70

psc

0.69

vy

0.68

anwhile

0.67

jury

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.