INDEX

Explanations

references to interpersonal relationships and social interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68

Prompts (Dashboard)

24,576 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

verifyException

-0.45

 MonoBehaviour

-0.42

CheckedChanged

-0.40

 bisherigen

-0.37

PerformLayout

-0.36

 ruban

-0.36

 esfuer

-0.36

 useEffect

-0.35

 farlo

-0.35

printStackTrace

-0.35

POSITIVE LOGITS

 ddelweddau

0.62

0.60

 additional

0.55

 snippetHide

0.54

additional

0.54

 opportunities

0.53

clusal

0.53

 fået

0.52

an

0.51

defin

0.51

Activations Density 0.132%

references to interpersonal relationships and social interactions

No Comments

No Known Activations