INDEX

Explanations

references to specific variables and data structures in programming or technical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.37.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

 AssemblyCulture

-0.59

+:+

-0.57

setVerticalGroup

-0.56

RTCK

-0.55

transQ

-0.54

+#+#

-0.53

 initComponents

-0.52

󠁢

-0.52

RenderAtEndOf

-0.52

ModelAdmin

-0.47

POSITIVE LOGITS

Ray

1.37

Jay

1.34

Bay

1.33

Ray

1.31

ray

1.30

ay

1.28

ay

1.27

bay

1.27

Jay

1.26

ray

1.25

Activations Density 0.856%

references to specific variables and data structures in programming or technical contexts

No Comments

No Known Activations