INDEX

Explanations

references to learning how to do something, specifically involving creation or production

oai_token-act-pair · gpt-3.5-turbo

instances of the word "make" and its variations

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

SPONSORED

-0.66

assis

-0.65

 Investigative

-0.65

 Regulatory

-0.64

 Niet

-0.64

 Accountability

-0.63

heter

-0.62

Mub

-0.61

 Leadership

-0.60

ei

-0.60

POSITIVE LOGITS

 sure

1.14

hift

0.97

 pilgr

0.89

 adjustments

0.86

 money

0.85

fun

0.81

 documentaries

0.81

 homemade

0.80

 mistakes

0.80

 headlines

0.80

Activations Density 0.138%

references to learning how to do something, specifically involving creation or production

instances of the word "make" and its variations

No Comments

No Known Activations