INDEX

Explanations

patterns involving numerical symbols and operators in a code or mathematical context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 للاسماء

-0.68

tors

-0.59

mobileqq

-0.58

IsContent

-0.57

-0.51

Post

-0.51

sib

-0.51

Eud

-0.50

scriptcase

-0.50

 gravid

-0.50

POSITIVE LOGITS

()*

0.91

*=

0.82

]*

0.78

])*

0.77

]*(

0.77

Xna

0.75

posedge

0.72

 ergibt

0.71

queryInterface

0.70

ActionCreators

0.69

Activations Density 0.464%

patterns involving numerical symbols and operators in a code or mathematical context

No Comments

No Known Activations