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

 Tsukuyomi

-0.81

EStream

-0.70

Origin

-0.70

 inspir

-0.69

 Feather

-0.64

 Severus

-0.63

arsity

-0.62

 difference

-0.61

ãĤº

-0.60

 Donation

-0.60

POSITIVE LOGITS

berman

0.94

jo

0.72

irements

0.70

sur

0.69

ija

0.69

bern

0.68

elected

0.68

bers

0.67

amus

0.67

enough

0.66

Activations Density 0.000%

No Known Activations

This feature has no known activations.