INDEX

Explanations

references to storage areas or storage-related items

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

Hentet

-0.75

GEBURTSDATUM

-0.72

antMatchers

-0.69

 Accesat

-0.66

InjectMocks

-0.62

GEBURTS

-0.61

 doInBackground

-0.60

isissez

-0.59

ValueStyle

-0.58

inWeight

-0.57

POSITIVE LOGITS

 closet

1.38

 cupboard

1.31

 Closet

1.22

 closets

1.17

 cupboards

1.12

closet

1.09

 cabinet

1.09

 shelves

1.07

 shelf

1.07

 cabinets

1.05

Activations Density 0.289%

references to storage areas or storage-related items

No Comments

No Known Activations