INDEX

Explanations

occurrences of the word "in" across different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

bewerken

-0.57

={`/

-0.56

ersdorf

-0.56

localPosition

-0.56

luc

-0.55

 Basi

-0.52

 Clio

-0.49

awtextra

-0.49

giu

-0.48

gol

-0.48

POSITIVE LOGITS

bibitem

0.70

anglement

0.68

ResumeLayout

0.66

 مرئيه

0.63

iciais

0.61

 onPostExecute

0.61

edance

0.60

seamnă

0.60

EDEFAULT

0.60

 amarillas

0.60

Activations Density 0.078%

occurrences of the word "in" across different contexts

No Comments

No Known Activations