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

 reper

-0.85

ushes

-0.79

uds

-0.79

 arrang

-0.72

 forks

-0.70

itives

-0.70

 sovere

-0.69

 sovereignty

-0.69

estyles

-0.68

 wallets

-0.67

POSITIVE LOGITS

Untitled

1.09

Story

0.98

Ast

0.82

Abstract

0.82

Mart

0.81

BACK

0.81

Study

0.80

Auth

0.80

Las

0.78

Card

0.78

Activations Density 0.000%

No Known Activations

This feature has no known activations.