INDEX

Explanations

references to personal experiences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

 dõi

-0.70

zugehen

-0.68

trivial

-0.66

 RoHS

-0.66

 Rabat

-0.66

AlterField

-0.62

betical

-0.62

htë

-0.61

 relâche

-0.60

SPARENT

-0.60

POSITIVE LOGITS

 experiences

1.60

 experience

1.56

 Experiences

1.51

 Experience

1.42

EXPERIENCE

1.41

Experience

1.40

 EXPERIENCE

1.35

Exper

1.35

 experien

1.34

experience

1.33

Activations Density 0.040%

references to personal experiences

No Comments

No Known Activations