INDEX

Explanations

numeric values and their representations

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

Mathematical or logical expressions

np_acts-logits-general · gemini-2.0-flash

numbers and code segments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 Anexo

-0.60

 crossorigin

-0.57

Efq

-0.57

Anexo

-0.54

 warszawa

-0.53

 eorum

-0.52

 ejus

-0.51

 depositphotos

-0.50

 Accessed

-0.50

 RIPRODUZIONE

-0.49

POSITIVE LOGITS

 ModelExpression

0.81

HideFlags

0.66

windowFixed

0.63

 Roskov

0.62

جغرافيا

0.62

TagMode

0.61

sbericht

0.61

 resultCode

0.59

NameInMap

0.58

ThroughAttribute

0.58

Activations Density 0.469%

numeric values and their representations

Mathematical or logical expressions

numbers and code segments

No Comments

No Known Activations