INDEX

Explanations

phrases related to loss or reduction

oai_token-act-pair · gpt-3.5-turbo

phrases indicating various types of losses or reductions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

Fax

-0.66

HQ

-0.64

better

-0.64

Nap

-0.63

Daily

-0.62

ombies

-0.62

fuck

-0.62

ctuary

-0.61

anu

-0.61

BSD

-0.59

POSITIVE LOGITS

 sorts

1.31

 consciousness

0.82

 hostilities

0.80

 funds

0.78

 goods

0.76

 limbs

0.75

 riches

0.70

 Funds

0.70

 electrons

0.70

 fortune

0.69

Activations Density 0.133%

phrases related to loss or reduction

phrases indicating various types of losses or reductions

No Comments

No Known Activations