INDEX

Explanations

mentions of "letter" or related concepts about correspondence

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

makeConstraints

-0.96

 propOrder

-0.86

Lähteet

-0.83

mylist

-0.77

hehehe

-0.74

Alike

-0.72

uesday

-0.71

-0.69

paravant

-0.69

foria

-0.69

POSITIVE LOGITS

 letters

1.71

 Letters

1.61

 LETTER

1.48

Letters

1.47

 Letter

1.41

 letter

1.41

letter

1.40

 LETTERS

1.40

letters

1.39

Letter

1.33

Activations Density 0.087%

mentions of "letter" or related concepts about correspondence

No Comments

No Known Activations