INDEX

Explanations

technical and programming terms related to data structure setups and APIs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

XmlAccessType

-0.76

 oprot

-0.70

="#"><

-0.67

PMailer

-0.65

 ContentValues

-0.64

 contextLoads

-0.61

 Roskov

-0.61

resave

-0.60

RTEX

-0.59

 CrossRef

-0.59

POSITIVE LOGITS

TODO

0.55

 module

0.52

 productive

0.52

valently

0.51

 aesthetics

0.51

atible

0.51

melo

0.50

страи

0.50

umos

0.50

 https

0.49

Activations Density 1.576%

technical and programming terms related to data structure setups and APIs

No Comments

No Known Activations