INDEX

Explanations

phrases indicating procedural or systematic actions

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 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

FXML

-0.53

źć

-0.48

erialization

-0.48

Parcelize

-0.46

usercontent

-0.44

NewUrlParser

-0.43

onomia

-0.42

äumt

-0.42

lhes

-0.41

etragen

-0.41

POSITIVE LOGITS

 above

3.50

above

3.10

Above

2.82

 Above

2.76

 aforementioned

2.54

 ABOVE

2.52

 acima

2.50

 mentioned

2.43

 aforesaid

2.38

mentioned

2.13

Activations Density 1.434%

phrases indicating procedural or systematic actions

No Comments

No Known Activations