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

itism

-0.76

WAYS

-0.73

cuts

-0.72

washing

-0.68

 McCarthy

-0.68

 Grimm

-0.66

 Manitoba

-0.65

landish

-0.64

town

-0.64

 Ramirez

-0.64

POSITIVE LOGITS

————

0.76

 boast

0.74

 Revel

0.71

 inherit

0.70

uble

0.68

lif

0.68

ken

0.67

fter

0.65

 dred

0.65

 coral

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.