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

iatus

-0.91

etheless

-0.74

adm

-0.72

agu

-0.70

ovie

-0.67

arious

-0.66

odox

-0.66

istance

-0.65

cember

-0.65

ebted

-0.65

POSITIVE LOGITS

 PACK

0.75

sters

0.73

TC

0.70

RAFT

0.67

 Stall

0.67

STER

0.67

 Crate

0.66

 hospitality

0.65

Sov

0.65

 Valhalla

0.65

Activations Density 0.000%

No Known Activations

This feature has no known activations.