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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

dig

-0.76

 Safari

-0.73

 GOODMAN

-0.71

SOURCE

-0.68

 ballpark

-0.67

 Curve

-0.66

heit

-0.65

 Commons

-0.63

Beer

-0.61

 Place

-0.59

POSITIVE LOGITS

chieve

0.87

secut

0.84

piring

0.81

iya

0.78

imov

0.76

aton

0.76

istar

0.76

idays

0.76

pects

0.74

mp

0.73

Activations Density 0.000%

No Known Activations

This feature has no known activations.