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

SPONSORED

-0.68

eq

-0.66

yl

-0.63

 Fargo

-0.63

icide

-0.63

 Shake

-0.62

 Rated

-0.62

ology

-0.61

bear

-0.61

Story

-0.61

POSITIVE LOGITS

omas

0.70

outher

0.69

 engagements

0.68

½

0.68

ãĤ§

0.68

ouver

0.66

ãĤ¨ãĥ«

0.66

oslav

0.66

ModLoader

0.66

Ñĥ

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.