INDEX

Explanations

terms related to interactions between different elements or variables

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

ValueStyle

-0.83

ⓧ

-0.77

 متعلقه

-0.77

StoreMessageInfo

-0.76

 estekak

-0.74

Geplaatst

-0.74

WithIOException

-0.74

']);

-0.73

"]);

-0.72

RegressionTest

-0.70

POSITIVE LOGITS

AxisAlignment

0.59

Sprintf

0.54

RectangleBorder

0.54

 inoxydable

0.53

hidupan

0.48

medriver

0.47

ViewImports

0.47

 StringBuffer

0.46

 محفوظة

0.45

tahui

0.45

Activations Density 0.623%

terms related to interactions between different elements or variables

No Comments

No Known Activations