INDEX

Explanations

terms related to documentation and application processes for various services

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

GraphicsUnit

-0.64

NOPQRST

-0.60

subpackage

-0.57

èdia

-0.54

ciclop

-0.53

WebVitals

-0.51

wpdb

-0.51

mbggenerated

-0.50

DockStyle

-0.49

delsen

-0.49

POSITIVE LOGITS

 previous

0.64

 passim

0.61

 proper

0.60

 previously

0.58

 contained

0.58

Portail

0.58

 attributable

0.57

requestCode

0.56

tagHelperRunner

0.56

RTLD

0.55

Activations Density 0.143%

terms related to documentation and application processes for various services

No Comments

No Known Activations