INDEX

Explanations

instances of the word "Maybe."

oai_token-act-pair · gpt-3.5-turbo

instances of the word "maybe."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 4-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.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.4.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

arthed

-0.87

cies

-0.85

lete

-0.83

ife

-0.82

ocaust

-0.80

ament

-0.80

aments

-0.73

ken

-0.73

ief

-0.73

rench

-0.72

POSITIVE LOGITS

 someday

1.04

 Acer

0.77

 SOME

0.70

 thats

0.67

 karma

0.67

 sensing

0.66

 subconscious

0.65

 Magnum

0.63

 forgive

0.63

 opio

0.62

Activations Density 0.029%

instances of the word "Maybe."

instances of the word "maybe."

No Comments

No Known Activations