INDEX

Explanations

references to various mathematical functions and their properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 myſelf

-1.17

 Jefus

-1.09

 themſelves

-1.08

 poffible

-1.08

 Monfieur

-1.01

 faſt

-0.99

 BorderRadius

-0.99

 doubtnut

-0.98

 himſelf

-0.98

 ſmall

-0.98

POSITIVE LOGITS

 function

1.63

 functions

1.62

 Function

1.55

Function

1.49

functions

1.48

function

1.42

 Functions

1.40

FUNCTION

1.35

 FUNCTION

1.32

Functions

1.31

Activations Density 0.105%

references to various mathematical functions and their properties

No Comments

No Known Activations