INDEX

Explanations

actions related to performing tasks or activities

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

before or related to performing an action

np_acts-logits-general · gemini-2.0-flash

performing actions

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

참고

-0.57

classnames

-0.53

 Marlow

-0.51

unehmen

-0.49

 apology

-0.47

 появление

-0.47

mpä

-0.46

 piłkarz

-0.46

pathy

-0.46

acry

-0.46

POSITIVE LOGITS

conducted

0.82

NUMX

0.80

performed

0.79

effectuer

0.78

 perform

0.76

 conducted

0.76

 performed

0.75

performs

0.72

+:+

0.72

 effectué

0.68

Activations Density 0.317%

actions related to performing tasks or activities

before or related to performing an action

performing actions

No Comments

No Known Activations