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

ILLE

-0.67

ween

-0.66

 mile

-0.61

oleon

-0.61

kinson

-0.61

 Upton

-0.58

 Skinner

-0.58

 Cotton

-0.58

upl

-0.57

rawdownloadcloneembedreportprint

-0.57

POSITIVE LOGITS

 Fathers

0.72

 TAMADRA

0.67

uci

0.66

shall

0.66

 fathers

0.65

itto

0.64

tsy

0.64

 Oath

0.63

pora

0.63

 Period

0.62

Activations Density 0.000%

No Known Activations

This feature has no known activations.