INDEX

Explanations

phrases related to auditory perception or the act of listening

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

CrossRef

-0.73

idavit

-0.72

Sub

-0.70

tieth

-0.69

 metav

-0.69

-0.68

ErrUnexpectedEOF

-0.68

 Produk

-0.67

 Picchu

-0.65

mages

-0.63

POSITIVE LOGITS

 hears

1.84

 hear

1.77

 Hear

1.75

 heard

1.72

 HEAR

1.66

Hear

1.59

 Heard

1.58

Heard

1.54

 Hearn

1.47

hear

1.42

Activations Density 0.046%

phrases related to auditory perception or the act of listening

No Comments

No Known Activations