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

 Tide

-0.79

illin

-0.75

IRC

-0.74

 Misc

-0.74

gged

-0.72

icking

-0.68

opped

-0.65

gging

-0.65

lyn

-0.64

Sport

-0.63

POSITIVE LOGITS

1.79

 VIDEOS

0.69

 âī

0.64

 shader

0.61

 veto

0.61

 variance

0.61

=~

0.60

esthetic

0.59

 Deity

0.57

ittal

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.