INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

*/(

-1.02

£ı

-0.86

CV

-0.83

 traged

-0.82

akespe

-0.82

itime

-0.81

irez

-0.77

cffff

-0.77

sembly

-0.77

 incent

-0.76

POSITIVE LOGITS

 Silver

0.70

 Born

0.65

sl

0.61

 Diego

0.60

 Colombian

0.60

Fal

0.60

 finally

0.59

 Sacramento

0.58

 Dominic

0.58

silver

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.