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

 Cutter

-0.66

âĨĳ

-0.65

acus

-0.64

ulner

-0.63

ghan

-0.62

ãĥ¼ãĤ¯

-0.62

jen

-0.62

phrine

-0.61

 inhibitor

-0.61

 Nets

-0.60

POSITIVE LOGITS

¿½

0.78

 Seym

0.77

awa

0.72

aturday

0.69

 âĶľâĶĢâĶĢ

0.69

ews

0.67

 misunder

0.66

 seiz

0.66

onday

0.66

 marqu

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.