INDEX

Explanations

technical terms and parameters related to permissions and variables

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 الرياضيه

-0.75

 Paglinawan

-0.53

хьтан

-0.52

HomeAsUpEnabled

-0.52

ждествен

-0.51

 חיצוניים

-0.51

 mxArray

-0.49

Supervis

-0.49

ThroughAttribute

-0.49

👈

-0.48

POSITIVE LOGITS

|}{}

0.66

}{*}{}

0.64

 للاسماء

0.62

}{*}{

0.62

 nhàng

0.61

ategorised

0.60

AndEndTag

0.58

TableHead

0.58

 république

0.58

 Référence

0.58

Activations Density 0.178%

technical terms and parameters related to permissions and variables

No Comments

No Known Activations