INDEX

Explanations

variables and parameters in code-like or mathematical notations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 louer

-0.53

 Prove

-0.52

✭✭

-0.49

Цита

-0.46

digkeit

-0.45

webElement

-0.45

plotly

-0.45

 mundiales

-0.45

 Dodson

-0.44

 ejus

-0.44

POSITIVE LOGITS

 consultato

0.86

="

0.76

 colspan

0.74

 rowspan

0.73

—"

0.71

 disponibilités

0.71

+"_

0.69

ArgsConstructor

0.68

ंदीखरीदारी

0.68

="_

0.66

Activations Density 0.089%

variables and parameters in code-like or mathematical notations

No Comments

No Known Activations