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

ntil

-0.74

ħĭ

-0.73

 reinforcement

-0.73

 easing

-0.70

Ĥİ

-0.70

 saline

-0.67

eeper

-0.67

 Reson

-0.66

 dens

-0.65

ebin

-0.65

POSITIVE LOGITS

icent

0.72

atos

0.69

antz

0.68

nard

0.66

ns

0.66

ggies

0.64

acio

0.64

cult

0.64

 Pigs

0.63

pir

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.