INDEX

Explanations

mentions or discussions of recognizing or acknowledging something

oai_token-act-pair · gpt-3.5-turbo

terms related to recognition and acknowledgment of statuses or contributions

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

quer

-0.74

ieri

-0.71

quin

-0.69

ovie

-0.68

ograp

-0.67

achus

-0.65

eware

-0.65

Synopsis

-0.64

çķ

-0.63

olit

-0.63

POSITIVE LOGITS

ledged

0.88

ibly

0.85

 shortcomings

0.82

 deficiencies

0.79

 that

0.75

 flaws

0.73

ances

0.72

 distinctions

0.72

 limitations

0.70

ibility

0.70

Activations Density 0.064%

mentions or discussions of recognizing or acknowledging something

terms related to recognition and acknowledgment of statuses or contributions

No Comments

No Known Activations