INDEX

Explanations

phrases related to directives or instructions

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "from."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 6-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.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

faced

-0.82

merce

-0.79

ratulations

-0.78

ierrez

-0.74

isphere

-0.74

certain

-0.73

pled

-0.72

icably

-0.69

 vulner

-0.69

accompan

-0.68

POSITIVE LOGITS

 afar

0.87

 Flavoring

0.82

 whence

0.80

 thence

0.73

 Cycling

0.72

 Adinida

0.71

 UNIVERS

0.67

 Elite

0.64

Elk

0.64

 Everett

0.63

Activations Density 0.027%

phrases related to directives or instructions

occurrences of the word "from."

No Comments

No Known Activations