INDEX

Explanations

instances of participation and involvement in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k

Configuration

google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.hook_mlp_out

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

 participation

-2.20

 participating

-2.02

 Participation

-2.00

 participate

-1.96

particip

-1.93

 participates

-1.91

 PARTICIP

-1.91

Participation

-1.91

participation

-1.89

Participating

-1.87

POSITIVE LOGITS

 ffilmiau

0.54

 SwitchCompat

0.52

👤

0.47

roid

0.47

ättä

0.47

avigation

0.47

ICIAS

0.47

Hentet

0.46

 NUKAT

0.45

roned

0.45

Activations Density 0.352%

instances of participation and involvement in various contexts

No Comments

No Known Activations