INDEX

Explanations

references to parks or park-related terminology

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

"Park" followed by a location

np_acts-logits-general · gemini-2.0-flash

park followed by common suffixes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 myſelf

-0.77

 Jefus

-0.71

دانشنامهٔ

-0.70

 purpoſe

-0.70

__':

-0.68

 Reſ

-0.67

Eſ

-0.67

 Diſ

-0.66

ymce

-0.66

 pleaſure

-0.65

POSITIVE LOGITS

 Parks

0.92

 parks

0.91

Parks

0.85

 Parkes

0.69

下载附件

0.67

PAR

0.67

parks

0.62

CodedInputStream

0.60

 rangers

0.60

PAR

0.59

Activations Density 0.189%

references to parks or park-related terminology

"Park" followed by a location

park followed by common suffixes

No Comments

No Known Activations