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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

psons

-0.81

issance

-0.80

poons

-0.75

uble

-0.75

Ã©n

-0.75

 gems

-0.74

 comprom

-0.70

vertisement

-0.69

 sentient

-0.69

poon

-0.69

POSITIVE LOGITS

iso

0.79

IDA

0.72

 correction

0.66

ia

0.63

 Viet

0.63

 Liberia

0.62

IA

0.62

cmp

0.61

ij

0.60

Box

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.