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

 throb

-0.84

ãĤ±

-0.76

acca

-0.76

 tremend

-0.74

 horr

-0.71

 plunder

-0.71

ugal

-0.71

 thrill

-0.68

awe

-0.67

 fucked

-0.66

POSITIVE LOGITS

 Guards

0.71

ARY

0.70

aries

0.69

ergy

0.69

 Buildings

0.68

 Deaths

0.66

 Turtles

0.66

 Pediatrics

0.65

 Environmental

0.63

zona

0.63

Activations Density 0.000%

No Known Activations

This feature has no known activations.