INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 3-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.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

 conduc

-0.77

Desk

-0.72

iking

-0.72

anu

-0.69

 destro

-0.69

ournals

-0.68

olas

-0.68

 Nost

-0.67

annis

-0.67

 nodd

-0.66

POSITIVE LOGITS

Draft

0.84

termination

0.72

ãĥĩãĤ£

0.72

position

0.70

`.

0.68

RFC

0.66

ILLE

0.65

iles

0.63

onent

0.60

 Territories

0.60

Activations Density 0.000%

No Known Activations

This feature has no known activations.