INDEX

Explanations

key findings or claims supported by research results

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

End of sentences

np_acts-logits-general · gemini-2.0-flash

scientific and technical writing

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

IntoConstraints

-0.58

帖最后由

-0.56

DockStyle

-0.56

 exactement

-0.53

exactly

-0.52

InitVars

-0.52

ClientSize

-0.52

الدراسه

-0.52

setVerticalGroup

-0.51

 Done

-0.51

POSITIVE LOGITS

elemField

0.59

 Keywords

0.58

ثيق

0.57

UserScript

0.56

nastics

0.56

rollup

0.55

']=$

0.55

 Biôgrafia

0.53

 Piso

0.53

encodeWith

0.52

Activations Density 0.576%

key findings or claims supported by research results

End of sentences

scientific and technical writing

No Comments

No Known Activations