INDEX

Explanations

mentions of the term "ma", likely in a context related to specific cultural or linguistic references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 Económica

-0.77

phazard

-0.77

uesday

-0.73

ViewFeatures

-0.72

 userSchema

-0.72

XmlAccessorType

-0.72

 '\\;'

-0.70

 tartalomajánló

-0.69

GEBURTSDATUM

-0.69

 Gurney

-0.69

POSITIVE LOGITS

ma

0.90

ма

0.60

PMailer

0.53

foo

0.53

GraphicsUnit

0.51

nodes

0.50

</em>

0.48

 FBref

0.47

Lut

0.46

pecia

0.45

Activations Density 0.063%

mentions of the term "ma", likely in a context related to specific cultural or linguistic references

No Comments

No Known Activations