INDEX

Explanations

key statistical or quantitative descriptors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

-0.81

ագրություններ

-0.72

 SwitchCompat

-0.72

पया

-0.67

Enllaces

-0.67

 bezeichneter

-0.66

новниш

-0.65

Viitteet

-0.64

ttemberg

-0.64

estacks

-0.64

POSITIVE LOGITS

NamedQueries

0.56

 eigenvalues

0.55

 extradition

0.53

('');

0.51

","");

0.51

 assurent

0.50

 legality

0.49

 Magistrate

0.49

 magistrate

0.49

 adverbs

0.48

Activations Density 0.375%

key statistical or quantitative descriptors

No Comments

No Known Activations