INDEX

Explanations

words related to three-dimensional shapes or objects

oai_token-act-pair · gpt-3.5-turbo

terms related to dimensions and dimensionality

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 follow

-0.68

 boom

-0.65

Hus

-0.64

 preced

-0.64

 Smith

-0.63

 pros

-0.63

 Brew

-0.63

 neigh

-0.63

 Brown

-0.62

AP

-0.62

POSITIVE LOGITS

dimensional

4.09

 dimensional

2.61

dimension

2.40

imensional

1.72

worldly

1.51

 dimension

1.38

 Dimension

1.32

sided

1.31

dim

1.24

 dimensions

1.19

Activations Density 0.018%

words related to three-dimensional shapes or objects

terms related to dimensions and dimensionality

No Comments

No Known Activations