INDEX

Explanations

specific durations and time-related measurements in context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

lacian

-0.46

 oseb

-0.44

ammans

-0.44

 onCancelled

-0.43

IsContent

-0.43

httphttps

-0.42

DeleteBehavior

-0.41

 initComponents

-0.41

 <=",

-0.41

gear

-0.37

POSITIVE LOGITS

 duration

0.93

duration

0.79

 longest

0.78

 durée

0.76

 Duration

0.75

 longer

0.74

 duración

0.74

Longer

0.73

 length

0.73

Duration

0.73

Activations Density 0.732%

specific durations and time-related measurements in context

No Comments

No Known Activations