INDEX

Explanations

terms related to fire and combustion

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Bins

-0.48

pholes

-0.43

TypedDataSet

-0.42

ربای

-0.42

CIS

-0.41

 Basse

-0.41

CWE

-0.41

 Swiss

-0.41

crata

-0.41

 Reverso

-0.40

POSITIVE LOGITS

 flame

1.41

 flames

1.30

Flame

1.24

 Flame

1.24

flame

1.15

 fire

1.00

 Flames

0.96

 flamme

0.96

 torches

0.92

 burning

0.92

Activations Density 0.239%

terms related to fire and combustion

No Comments

No Known Activations