INDEX

Explanations

sequences of numerical values and symbols typically used in programming contexts

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

Code snippets with bracketed numbers

np_acts-logits-general · gemini-2.0-flash

list context surrounding numbers

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

__(/*!

-0.68

Sucesor

-0.65

|}{}

-0.65

 externi

-0.64

')))

-0.63

 الرخصة

-0.61

ModelAdmin

-0.60

Становништво

-0.59

 contextLoads

-0.58

 doInBackground

-0.57

POSITIVE LOGITS

WriteTagHelper

0.59

_,

0.53

ModelSerializer

0.53

imab

0.52

?,?,

0.52

omitempty

0.51

றி

0.50

 Commissioners

0.49

+,

0.49

ampunk

0.49

Activations Density 0.640%

sequences of numerical values and symbols typically used in programming contexts

Code snippets with bracketed numbers

list context surrounding numbers

No Comments

No Known Activations