INDEX

Explanations

references to code examples or resources for troubleshooting and clarification

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

Links to external resources/articles

np_acts-logits-general · gemini-2.0-flash

links to resources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

addContainerGap

-0.38

Tazama

-0.38

 CreateTagHelper

-0.37

 unknownFields

-0.37

 onCreateView

-0.35

MockMvc

-0.31

 HasFactory

-0.30

 retail

-0.30

 SqlCommand

-0.30

setContentView

-0.30

POSITIVE LOGITS

].

0.50

SystemColors

0.48

UserScript

0.48

.[/

0.47

ulongan

0.47

 Diarsipkan

0.47

0.46

]?.

0.46

).

0.45

 nonUne

0.45

Activations Density 0.368%

references to code examples or resources for troubleshooting and clarification

Links to external resources/articles

links to resources

No Comments

No Known Activations