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

loo

-0.74

rarily

-0.70

ench

-0.66

 artif

-0.65

ikarp

-0.64

iosyncr

-0.63

gae

-0.62

etheless

-0.61

ii

-0.61

doms

-0.60

POSITIVE LOGITS

 CLSID

0.69

 filibuster

0.65

 Shutdown

0.63

Loader

0.61

nic

0.61

andre

0.60

uten

0.58

igo

0.58

Plugin

0.58

 Machina

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.