INDEX

Explanations

sections of text that contain delineating comments or markers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

principalColumn

-0.64

InjectAttribute

-0.61

 Vikipedi

-0.59

IndentedString

-0.55

IVEREF

-0.54

 ffilmiau

-0.53

DebuggerStep

-0.53

}{@

-0.52

verwijspagina

-0.52

bootstrapcdn

-0.52

POSITIVE LOGITS

徨

0.49

0.48

0.47

 compleanno

0.46

0.43

 cammino

0.42

the

0.40

Activations Density 0.387%

sections of text that contain delineating comments or markers

No Comments

No Known Activations

sections of text that contain delineating comments or markers

No Comments

No Known Activations