INDEX

Explanations

references to cars and related vehicles

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

cars

np_acts-logits-general · gemini-2.0-flash

car and subsequent words

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 '\\;'

-0.85

 NSCoder

-0.66

########.

-0.66

ftagPool

-0.65

WriteTagHelper

-0.63

 Roskov

-0.61

IsContent

-0.58

 Himo

-0.58

Jeografia

-0.56

inSlope

-0.54

POSITIVE LOGITS

abinieri

0.71

 owners

0.69

 parked

0.66

 owner

0.63

 registrations

0.63

 rental

0.62

 rentals

0.61

 registration

0.59

 wreckage

0.59

 Owners

0.58

Activations Density 0.244%

references to cars and related vehicles

cars

car and subsequent words

No Comments

No Known Activations