INDEX

Explanations

repeated phrases related to relationships, frameworks, and observations

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

Prepositions and articles

np_acts-logits-general · gemini-2.0-flash

these and such descriptors

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

RuleContext

-0.60

epam

-0.52

rigation

-0.51

PYX

-0.50

</em>

-0.47

 Beres

-0.47

…

-0.46

ARDO

-0.46

board

-0.45

ICIA

-0.45

POSITIVE LOGITS

 этими

0.79

このような

0.77

そのような

0.71

 Audiodateien

0.70

こうした

0.70

mybatisplus

0.69

 Эти

0.69

 these

0.67

こういった

0.66

このように

0.66

Activations Density 1.236%

repeated phrases related to relationships, frameworks, and observations

Prepositions and articles

these and such descriptors

No Comments

No Known Activations