INDEX

Explanations

keywords and key terms related to programming and encoding specifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

['$

-0.66

 onBind

-0.65

AsUp

-0.65

 INTERESAR

-0.64

Trama

-0.63

::{

-0.62

aarrggbb

-0.62

❯

-0.61

Lá

-0.59

PhysRevLett

-0.59

POSITIVE LOGITS

 colspan

3.47

 rowspan

1.09

multicolumn

0.97

enumi

0.91

enumii

0.70

 محفوظة

0.63

multirow

0.61

WebKit

0.60

 surla

0.60

 pinulongan

0.60

Activations Density 0.006%

keywords and key terms related to programming and encoding specifications

No Comments

No Known Activations