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

 aven

-0.73

nex

-0.71

 propri

-0.67

 apiece

-0.67

 respawn

-0.63

::::::::

-0.63

 ammunition

-0.62

 expire

-0.62

 proport

-0.61

 brass

-0.61

POSITIVE LOGITS

letters

0.93

Walker

0.74

Independent

0.73

ESCO

0.71

WS

0.70

shown

0.69

 Taxi

0.69

 Rated

0.66

Hamilton

0.66

IAS

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.