INDEX

Explanations

programming concepts, particularly related to function and variable definitions and calls

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

Code snippets and variable/object names in code

np_acts-logits-general · gemini-2.0-flash

code constructs and keywords

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

tvguidetime

-0.82

 doubtnut

-0.73

 photolibrary

-0.72

 aéreo

-0.72

CloseOperation

-0.69

setVerticalGroup

-0.68

ProcessEvent

-0.67

HasForeignKey

-0.67

 volontaire

-0.67

DeleteBehavior

-0.67

POSITIVE LOGITS

?>/

0.70

$("#

0.66

 $("#

0.62

$(".

0.59

aval

0.58

$('#

0.58

=$("#

0.58

_('

0.57

iso

0.56

($"{

0.56

Activations Density 0.756%

programming concepts, particularly related to function and variable definitions and calls

Code snippets and variable/object names in code

code constructs and keywords

No Comments

No Known Activations