INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

ITED

-0.85

zbollah

-0.84

reads

-0.81

iets

-0.80

-0.76

QUI

-0.75

STE

-0.72

iken

-0.72

thritis

-0.70

ãĥīãĥ©

-0.69

POSITIVE LOGITS

ĨĴ

1.03

ļéĨĴ

0.90

²¾

0.77

Ħ¢

0.69

£ı

0.68

ĺħ

0.68

Ĺ

0.67

¶ħ

0.67

ģ

0.66

 ende

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.