INDEX

Explanations

technical terms related to quantitative analysis

oai_token-act-pair · gpt-3.5-turbo

terms that indicate measurement and quantification

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 8-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.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

HOME

-0.76

opsis

-0.72

ortium

-0.66

nen

-0.64

vic

-0.64

 purse

-0.63

 Legs

-0.61

 Mansion

-0.59

Mi

-0.59

osaurus

-0.59

POSITIVE LOGITS

itatively

1.51

ifiable

1.00

imet

0.96

 quant

0.91

 easing

0.90

itative

0.83

ified

0.81

quant

0.80

ãĤ¡

0.78

idian

0.78

Activations Density 0.055%

technical terms related to quantitative analysis

terms that indicate measurement and quantification

No Comments

No Known Activations