INDEX

Explanations

references to DataFrames in coding or data analysis contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

+#+

-0.61

anyol

-0.55

 الحره

-0.54

蜀

-0.53

Okey

-0.53

 particules

-0.52

 pasaj

-0.52

ink

-0.50

uş

-0.48

AccessorTable

-0.48

POSITIVE LOGITS

dst

0.67

 BorderRadius

0.65

="<?=

0.64

Sti

0.61

JVM

0.61

Piz

0.60

 circumstances

0.60

DST

0.59

 neceff

0.59

papar

0.58

Activations Density 0.094%

references to DataFrames in coding or data analysis contexts

No Comments

No Known Activations