INDEX

Explanations

instances of the word "Maybe" to indicate uncertainty or possibility

oai_token-act-pair · gpt-3.5-turbo

occurrences of the word "maybe" and its variations, indicating uncertainty or speculation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 11-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.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

ocaust

-0.77

dayName

-0.75

cies

-0.74

arthed

-0.73

ãĥ£

-0.72

ament

-0.71

cedented

-0.71

ventures

-0.71

folios

-0.70

iak

-0.69

POSITIVE LOGITS

 someday

1.41

 even

1.00

 sooner

0.89

 EVEN

0.80

 next

0.79

 tomorrow

0.76

 unsurprisingly

0.74

 they

0.74

 somebody

0.74

 sometime

0.72

Activations Density 0.054%

instances of the word "Maybe" to indicate uncertainty or possibility

occurrences of the word "maybe" and its variations, indicating uncertainty or speculation

No Comments

No Known Activations