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

daq

-0.72

pour

-0.71

 fortune

-0.69

antha

-0.67

 Sawyer

-0.66

 Rockefeller

-0.65

stress

-0.64

sell

-0.64

 Chomsky

-0.64

querque

-0.63

POSITIVE LOGITS

GU

0.69

Ñģ

0.68

uru

0.65

imet

0.64

romy

0.62

Ð»

0.61

0.60

KI

0.60

çīĪ

0.60

HA

0.59

Activations Density 0.000%

No Known Activations

This feature has no known activations.