INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

leck

-0.69

 browsing

-0.68

irect

-0.67

 Pictures

-0.66

lections

-0.64

 witnessing

-0.64

soType

-0.63

ime

-0.62

mpeg

-0.62

abase

-0.62

POSITIVE LOGITS

iggs

0.82

roth

0.75

bread

0.70

VILLE

0.69

hig

0.68

 Fiesta

0.68

nir

0.65

Ĥİ

0.64

hig

0.64

kaya

0.64

Activations Density 0.000%

No Known Activations

This feature has no known activations.