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

unity

-0.73

Tag

-0.70

rontal

-0.69

munition

-0.69

bolt

-0.69

Oak

-0.67

emon

-0.67

rition

-0.66

Sop

-0.65

ears

-0.65

POSITIVE LOGITS

 Quarterly

0.66

iciary

0.63

iesel

0.63

 stagger

0.63

iche

0.62

 Categories

0.62

 encyclopedia

0.61

 Quote

0.60

 Employees

0.60

 Journals

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.