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

anim

-0.70

voice

-0.64

 favoured

-0.63

Cola

-0.63

 favored

-0.62

landish

-0.61

Stew

-0.60

 Sandwich

-0.60

 Sponge

-0.59

POSITIVE LOGITS

ortmund

0.88

 regress

0.84

orgetown

0.82

ibaba

0.74

bernatorial

0.71

ctors

0.71

illance

0.67

neapolis

0.66

ivari

0.66

 Brach

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.