INDEX

Explanations

expressions of imagination and hypothetical scenarios

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 alimentaria

-0.40

strij

-0.40

 alimentaire

-0.38

égard

-0.38

 Holiness

-0.37

ostante

-0.37

 helft

-0.37

 kolej

-0.36

roa

-0.36

 Administrativna

-0.36

POSITIVE LOGITS

 imagine

0.88

 Imagine

0.87

Imagine

0.87

imagine

0.82

 imagined

0.76

 imagining

0.73

 IMAG

0.72

 Imagin

0.72

 scenarios

0.69

 imaginable

0.69

Activations Density 0.179%

expressions of imagination and hypothetical scenarios

No Comments

No Known Activations