INDEX

Explanations

the word "Motivation" and variations of it

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "Mot" or its variations, indicating a focus on motivational content

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 10-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.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

theless

-0.72

 Hades

-0.66

 Sinclair

-0.65

 Silence

-0.65

 scissors

-0.65

 Moonlight

-0.64

 Hasan

-0.63

 Hitman

-0.63

 Leopard

-0.62

 Ming

-0.61

POSITIVE LOGITS

ivated

1.64

ivation

1.60

ivating

1.44

Ã¶r

1.21

oring

1.19

iv

1.13

orem

1.12

ility

1.07

ypes

1.07

itious

1.05

Activations Density 0.024%

the word "Motivation" and variations of it

occurrences of the word "Mot" or its variations, indicating a focus on motivational content

No Comments

No Known Activations