INDEX

Explanations

phrases indicating uncertainty or speculation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

PMailer

-0.55

 hush

-0.54

 fibrin

-0.53

 jurisprudence

-0.53

 appreciating

-0.52

 Corresponding

-0.51

 Plutarch

-0.51

Tout

-0.50

 Tout

-0.50

Sied

-0.50

POSITIVE LOGITS

IsMutable

0.75

 CanadaChoose

0.73

__*/

0.72

writeFieldEnd

0.65

Étymologie

0.64

 propOrder

0.63

adpleegd

0.62

 Drapeau

0.61

libft

0.60

 AssemblyCulture

0.59

Activations Density 0.341%

phrases indicating uncertainty or speculation

No Comments

No Known Activations