INDEX

Explanations

fractions in a recipe

oai_token-act-pair · gpt-3.5-turbo

fractions and measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

 Fletcher

-0.80

 Elliott

-0.78

 Burgess

-0.70

 Dragonbound

-0.69

Syl

-0.68

 Elliot

-0.68

 Chandler

-0.65

 Leilan

-0.65

 Daly

-0.63

 Gustav

-0.63

POSITIVE LOGITS

pmwiki

1.07

oct

1.05

carbon

1.00

0.94

lvl

0.89

story

0.89

site

0.88

Flickr

0.88

0.87

Activations Density 0.036%

fractions in a recipe

fractions and measurements

No Comments

No Known Activations