INDEX

Explanations

positive feedback about services and interactions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.36.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

PostInfinity

-0.52

stateMutability

-0.46

AsUp

-0.45

ValueStyle

-0.45

unknownFields

-0.45

 "..\..\..\

-0.45

DockStyle

-0.44

Parcours

-0.44

SequentialGroup

-0.43

httphttps

-0.40

POSITIVE LOGITS

 genuinely

0.86

 listens

0.85

 listened

0.79

 listen

0.77

 LISTEN

0.73

 patiently

0.68

 cares

0.67

 Listen

0.65

 truly

0.65

genu

0.65

Activations Density 0.164%

positive feedback about services and interactions

No Comments

No Known Activations