INDEX

Explanations

references to sample sizes in data analysis

oai_token-act-pair · gpt-3.5-turbo

references to samples and their sizes in research contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ledged

-0.71

der

-0.69

ModLoader

-0.65

die

-0.65

lesiastical

-0.65

 marqu

-0.65

zzi

-0.63

standing

-0.63

lvl

-0.62

swick

-0.62

POSITIVE LOGITS

 sizes

0.98

 size

0.93

meal

0.81

 collection

0.80

alogy

0.79

 collected

0.75

 thereof

0.74

icles

0.74

 Collection

0.73

 collections

0.73

Activations Density 0.055%

references to sample sizes in data analysis

references to samples and their sizes in research contexts

No Comments

No Known Activations