INDEX

Explanations

references to annual events or reports

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

InSection

-0.68

HomeAsUpEnabled

-0.66

AccessorTable

-0.65

 GetEnumerator

-0.56

Kef

-0.52

GrantedAuthority

-0.51

 uninstalled

-0.50

ViewFeatures

-0.49

tagext

-0.47

 Eisenhower

-0.46

POSITIVE LOGITS

 yearly

0.71

 brukar

0.69

 annual

0.68

 annually

0.62

annual

0.61

 Yearly

0.61

Annual

0.59

 Annual

0.59

毎年

0.59

 seasonal

0.58

Activations Density 0.294%

references to annual events or reports

No Comments

No Known Activations