INDEX

Explanations

code-related operations and methods specifically for handling data extraction and conversion

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

Code snippets or conversions

np_acts-logits-general · gemini-2.0-flash

determine, get, convertTo

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gonic

-0.71

 viewDidLoad

-0.64

 typelib

-0.61

DataAnnotations

-0.60

WebVitals

-0.60

OGND

-0.59

diel

-0.53

 BorderSide

-0.52

AccessorTable

-0.52

 fans

-0.51

POSITIVE LOGITS

ValueStyle

0.69

 GENERATED

0.67

 appropriate

0.64

 engraçadas

0.62

ьаж

0.62

 naselje

0.61

 hendes

0.59

 صوتيه

0.59

 feroit

0.59

muerzo

0.59

Activations Density 0.205%

code-related operations and methods specifically for handling data extraction and conversion

Code snippets or conversions

determine, get, convertTo

No Comments

No Known Activations