INDEX

Explanations

No Explanations Found

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 1-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.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

 hypot

-0.76

eln

-0.73

scl

-0.71

 lett

-0.71

 pellets

-0.70

enthal

-0.69

cule

-0.68

 destro

-0.68

rag

-0.68

 pulp

-0.67

POSITIVE LOGITS

EMBER

0.80

PLA

0.73

ATA

0.72

................

0.71

IDENT

0.70

FN

0.69

IPP

0.69

ULTS

0.69

........

0.68

OWS

0.68

Activations Density 0.000%

No Known Activations

This feature has no known activations.