INDEX

Explanations

terms related to mathematical functions and models

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

fatalError

-0.60

SaveChangesAsync

-0.58

Dagger

-0.56

 Quay

-0.54

 slip

-0.52

 cliquez

-0.52

pheres

-0.51

 haplo

-0.51

 consultato

-0.50

ArgsConstructor

-0.50

POSITIVE LOGITS

RenderAtEndOf

0.80

 curve

0.70

 ModelExpression

0.69

 curves

0.64

 kaynağından

0.62

RegressionTest

0.60

ArrowToggle

0.57

curve

0.55

NameInMap

0.55

formula

0.53

Activations Density 1.410%

terms related to mathematical functions and models

No Comments

No Known Activations