INDEX

Explanations

references to streets and street-related concepts

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

"Street" followed by transportation words

np_acts-logits-general · gemini-2.0-flash

streetcar

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

atever

-0.63

 rosette

-0.62

{}{}

-0.61

educational

-0.61

ModelAdmin

-0.61

 Turch

-0.60

 handleMessage

-0.60

 Parton

-0.59

 Permanente

-0.59

itives

-0.59

POSITIVE LOGITS

Streets

0.75

 Streets

0.73

 streets

0.71

 street

0.65

corner

0.64

WebServlet

0.63

 corner

0.59

streets

0.58

car

0.58

 Street

0.58

Activations Density 0.038%

references to streets and street-related concepts

"Street" followed by transportation words

streetcar

No Comments

No Known Activations