INDEX

Explanations

parentheses and related syntax in code

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

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

 iprot

-0.73

-0.72

NewUrlParser

-0.69

Tē

-0.65

-0.64

OGND

-0.63

("");

-0.62

 متعلقه

-0.60

 disambiguazione

-0.60

adpleegd

-0.60

POSITIVE LOGITS

↵

0.91

0.69

__":

0.53

__":

0.51

__':

0.51

 suivants

0.49

$}}

0.47

__':

0.45

</h3>

0.44

Activations Density 0.063%

parentheses and related syntax in code

No Comments

No Known Activations