INDEX

Explanations

statements indicating logical progression or proof structure

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

<()>

-0.61

 onPostExecute

-0.54

KEYCODE

-0.52

expandindo

-0.51

 خارجية

-0.49

LogFactory

-0.49

SBATCH

-0.48

 تضيفلها

-0.47

 Pilate

-0.46

!(:

-0.46

POSITIVE LOGITS

处的

0.56

')";

0.56

']):

0.55

 Principle

0.54

 לפי

0.54

 Theorem

0.54

 GenerationType

0.53

Principle

0.51

neries

0.51

})^

0.50

Activations Density 0.939%

statements indicating logical progression or proof structure

No Comments

No Known Activations