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

ovo

-0.82

hent

-0.78

afort

-0.77

usky

-0.74

hern

-0.72

assis

-0.69

ameron

-0.67

chnology

-0.67

ped

-0.66

adesh

-0.66

POSITIVE LOGITS

izable

0.66

Cooldown

0.63

 difficulty

0.61

Token

0.61

 heartbeat

0.61

 cooldown

0.61

 Oprah

0.60

 bumps

0.59

 listeners

0.59

izers

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.