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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Intent

-0.69

 Jays

-0.69

 timers

-0.68

 Plex

-0.65

 jQuery

-0.65

paw

-0.64

 tuning

-0.63

 resume

-0.61

 Kodi

-0.61

ult

-0.60

POSITIVE LOGITS

irgin

0.84

oya

0.78

pell

0.74

lished

0.73

LOD

0.71

Smith

0.69

usalem

0.68

solid

0.68

native

0.67

iqueness

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.