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

ussen

-0.72

 nutshell

-0.71

isks

-0.71

 Lank

-0.70

ighed

-0.69

uminum

-0.69

 nickel

-0.69

inh

-0.67

irt

-0.67

 serv

-0.67

POSITIVE LOGITS

Beast

0.94

Cat

0.81

atively

0.80

Organ

0.78

soType

0.77

track

0.75

Events

0.75

XM

0.74

TM

0.74

Catal

0.74

Activations Density 0.000%

No Known Activations

This feature has no known activations.