INDEX

Explanations

language related to ignition and combustion processes

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

reonine

-0.61

elemField

-0.58

GOTREF

-0.58

rimidine

-0.56

ModelAdmin

-0.56

Cucumber

-0.55

rinfo

-0.55

siella

-0.54

 vacu

-0.52

oluted

-0.51

POSITIVE LOGITS

 flames

1.33

 flame

1.24

 fire

1.24

 embers

1.14

 fires

1.14

 Flames

1.11

 arson

1.09

 Flame

1.07

fire

1.06

 ignited

1.06

Activations Density 0.198%

language related to ignition and combustion processes

No Comments

No Known Activations