INDEX

Explanations

quantitative expressions or mathematical constructs, particularly in the context of programming or data analysis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

use

-0.45

心的

-0.44

 הז

-0.42

adjoint

-0.41

 Beat

-0.41

óngase

-0.39

 Cess

-0.39

mede

-0.39

 hefyd

-0.39

 mulher

-0.39

POSITIVE LOGITS

MigrationBuilder

0.86

WEBPACK

0.69

исленность

0.69

BeginContext

0.68

 समीक्षक

0.67

 Roskov

0.66

SourceChecksum

0.64

aarrggbb

0.63

 nakalista

0.63

Хьажоргаш

0.63

Activations Density 1.229%

quantitative expressions or mathematical constructs, particularly in the context of programming or data analysis

No Comments

No Known Activations