INDEX

Explanations

expressions related to assessment or evaluation

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

followed by reflexive pronouns

np_acts-logits-general · gemini-2.0-flash

consider oneself

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 Lordships

-0.48

Tentang

-0.41

 rappelle

-0.39

 putea

-0.39

seros

-0.39

 scuro

-0.39

}:${

-0.38

 gevo

-0.37

Czy

-0.35

stawa

-0.35

POSITIVE LOGITS

 himself

1.45

 themselves

1.45

 ourselves

1.44

 yourself

1.42

themselves

1.40

 herself

1.38

 myself

1.33

 itself

1.29

himself

1.28

itself

1.27

Activations Density 0.361%

expressions related to assessment or evaluation

followed by reflexive pronouns

consider oneself

No Comments

No Known Activations