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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

BuyableInstoreAndOnline

-0.99

gence

-0.76

 Charity

-0.72

GGGG

-0.70

NESS

-0.70

ãĤ¦

-0.69

 Bett

-0.68

 Chocobo

-0.67

 Kinn

-0.67

ãĥ´

-0.66

POSITIVE LOGITS

 macros

0.75

 entitle

0.70

sq

0.68

bytes

0.66

 procedures

0.65

aths

0.64

ask

0.63

utils

0.62

paper

0.61

 substr

0.61

Activations Density 0.000%

No Known Activations

This feature has no known activations.