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

 Mayer

-0.66

 Kardashian

-0.63

 Beaut

-0.62

 Invest

-0.62

 Mobile

-0.62

 Site

-0.61

 Mint

-0.60

 Schwar

-0.60

 Persona

-0.60

 Photographer

-0.59

POSITIVE LOGITS

vae

0.89

ropy

0.80

Sov

0.79

matter

0.78

animate

0.77

hang

0.77

rase

0.77

tera

0.75

ragon

0.73

hus

0.73

Activations Density 0.000%

No Known Activations

This feature has no known activations.