INDEX

Explanations

phrases that indicate partiality or incompleteness

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

 Roskov

-0.85

المناصب

-0.79

 SwitchCompat

-0.74

rrggbb

-0.69

GraphicsUnit

-0.67

 NDEBUG

-0.67

 anhyd

-0.66

 convulsions

-0.66

expandindo

-0.65

 widest

-0.63

POSITIVE LOGITS

 part

0.97

 portion

0.91

 parte

0.86

一部分

0.81

part

0.79

 portions

0.76

 PART

0.75

 parts

0.74

Portion

0.74

 PARTE

0.74

Activations Density 0.402%

phrases that indicate partiality or incompleteness

No Comments

No Known Activations