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

poons

-0.77

hops

-0.69

inks

-0.67

perty

-0.65

HUD

-0.65

 gazing

-0.63

ouses

-0.63

ģĸ

-0.63

licks

-0.62

 appre

-0.61

POSITIVE LOGITS

anon

0.74

esson

0.74

 background

0.69

itar

0.66

rio

0.63

ryan

0.63

ust

0.62

BLIC

0.62

OC

0.61

vance

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.