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

 Franch

-0.84

 Bounty

-0.75

ModLoader

-0.73

Â¯Â¯Â¯Â¯Â¯Â¯Â¯Â¯

-0.71

RECT

-0.69

 Ares

-0.69

Mao

-0.69

 Motorsport

-0.69

 Kron

-0.68

Yel

-0.68

POSITIVE LOGITS

earable

0.85

 reuse

0.70

 enrichment

0.67

cest

0.66

induced

0.65

 succeed

0.65

 fallout

0.64

 flap

0.63

verage

0.63

opian

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.