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

htaking

-0.74

ories

-0.70

vic

-0.70

aunder

-0.69

 reconstructed

-0.69

arij

-0.68

iterranean

-0.67

hetic

-0.66

senal

-0.66

ngth

-0.66

POSITIVE LOGITS

rule

0.73

Scale

0.68

rum

0.64

jah

0.63

"]=>

0.63

dB

0.63

Privacy

0.63

 Mavericks

0.62

nm

0.62

 ROCK

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.