INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.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

mn

-0.65

tackle

-0.64

uffle

-0.63

Haunted

-0.61

aunting

-0.60

mount

-0.60

 moon

-0.59

ipher

-0.58

mania

-0.58

haps

-0.58

POSITIVE LOGITS

 Gard

0.82

opted

0.72

itial

0.69

 Processing

0.67

cov

0.65

 Jensen

0.63

 ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³

0.63

 Transit

0.62

 Chemical

0.62

ITS

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.