INDEX

Explanations

words related to dimensions or three-dimensional objects

oai_token-act-pair · gpt-3.5-turbo

references to dimensions and dimensionality in various contexts

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

soDeliveryDate

-0.86

doms

-0.80

skill

-0.77

ãģį

-0.76

oaded

-0.75

ortium

-0.74

wick

-0.71

ublic

-0.71

tty

-0.70

yright

-0.69

POSITIVE LOGITS

ality

1.00

imensional

0.88

 dimension

0.86

 dimensions

0.81

ally

0.79

arium

0.79

 Nept

0.78

 dimensional

0.76

 gravity

0.73

ĸļ

0.72

Activations Density 0.057%

words related to dimensions or three-dimensional objects

references to dimensions and dimensionality in various contexts

No Comments

No Known Activations