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

 Weed

-0.71

 fundament

-0.70

 Cheong

-0.68

Draw

-0.67

Dialogue

-0.66

Rect

-0.66

WARE

-0.66

 Nadu

-0.64

ARDS

-0.64

Hardware

-0.63

POSITIVE LOGITS

 transcripts

0.74

netflix

0.72

rab

0.72

 respondent

0.68

ixtape

0.67

rase

0.67

rat

0.66

burgh

0.65

rus

0.65

iaries

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.