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

ãģ®éŃĶ

-0.82

ledged

-0.76

steen

-0.75

owsky

-0.72

à¥

-0.68

 Guru

-0.65

 Punjab

-0.65

inational

-0.64

Duo

-0.64

 Gujar

-0.63

POSITIVE LOGITS

 fear

0.74

AE

0.64

 envy

0.61

 mistrust

0.61

HUD

0.61

CVE

0.61

Status

0.58

 itch

0.57

--------------------

0.57

 nuts

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.