INDEX

Explanations

words related to stroke

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

ValueStyle

-0.76

 shewn

-0.65

 primario

-0.64

 citoy

-0.64

 препратки

-0.64

 natale

-0.63

 fotográfico

-0.61

 geest

-0.60

 Riproduzione

-0.60

 auroit

-0.60

POSITIVE LOGITS

 STRO

0.73

ams

0.73

oms

0.68

stroke

0.64

{{/

0.61

")[

0.61

%");

0.61

bukkit

0.60

getDescriptor

0.60

 stroke

0.59

Activations Density 0.099%

words related to stroke

No Comments

No Known Activations