INDEX

Explanations

keywords related to disqualifications and forfeitures

oai_token-act-pair · gpt-3.5-turbo

terms related to disqualification and forfeiture

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

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Operation

-0.70

 Lans

-0.70

 pastoral

-0.69

OTOS

-0.67

ttp

-0.65

 Vive

-0.63

ï¸ı

-0.61

 Airl

-0.61

yll

-0.60

TPP

-0.59

POSITIVE LOGITS

 disqual

1.62

 disqualified

1.49

ifications

0.93

ifying

0.92

ifies

0.89

ify

0.85

ifiers

0.84

 ineligible

0.82

 qualifications

0.81

ifier

0.80

Activations Density 0.006%

keywords related to disqualifications and forfeitures

terms related to disqualification and forfeiture

No Comments

No Known Activations