INDEX

Explanations

conversations involving sensory experiences and emotional reactions

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

hearing or having heard

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

RTSN

-0.33

Appointment

-0.32

SystemColors

-0.32

 Profit

-0.31

ExternalTask

-0.31

behaviour

-0.31

 algo

-0.30

 Locomotive

-0.30

 Sén

-0.30

README

-0.30

POSITIVE LOGITS

 hear

1.46

 heard

1.43

 hears

1.38

heard

1.22

 hearing

1.21

hear

1.21

 Hear

1.20

Hear

1.18

 Hearing

1.12

 HEAR

1.07

Activations Density 0.029%

conversations involving sensory experiences and emotional reactions

hearing or having heard

No Comments

No Known Activations