INDEX

Explanations

terms related to social behaviors and classifications of individuals

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

ending with suffixes

np_acts-logits-general · gemini-2.0-flash

genetic, personality, configuration, stream

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

 nahilalakip

-0.62

AndEndTag

-0.61

webElementXpaths

-0.61

ScopeManager

-0.60

+#+#

-0.58

httphttps

-0.54

__(/*!

-0.53

AddTagHelper

-0.52

 CreateTagHelper

-0.52

 EconPapers

-0.52

POSITIVE LOGITS

EndGlobalSection

0.41

XtraGrid

0.39

 заключается

0.38

 polega

0.37

 znaczy

0.33

 คือ

0.33

SHADER

0.32

といって

0.32

 refers

0.31

 innebär

0.31

Activations Density 0.855%

terms related to social behaviors and classifications of individuals

ending with suffixes

genetic, personality, configuration, stream

No Comments

No Known Activations