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

 blat

-0.75

;;;;

-0.71

LLP

-0.69

CLR

-0.66

 explan

-0.65

 detrim

-0.63

RL

-0.63

 Nightmares

-0.63

HQ

-0.62

 defe

-0.61

POSITIVE LOGITS

owship

0.66

uctor

0.65

anka

0.65

icht

0.62

boa

0.61

 REPORT

0.60

ellen

0.59

bor

0.59

anca

0.57

Ã³

0.57

Activations Density 0.000%

No Known Activations

This feature has no known activations.