INDEX

Explanations

occurrences of the word "in" and its variants in different contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 تضيفلها

-0.61

 HasFactory

-0.59

 desmotivaciones

-0.57

 eccell

-0.56

ScopeManager

-0.55

 geda

-0.54

 semelh

-0.54

 laſſen

-0.54

Gweler

-0.52

bootstrapcdn

-0.52

POSITIVE LOGITS

IN

0.66

IN

0.60

in

0.59

In

0.59

 inside

0.59

0.56

 Inside

0.55

 insiders

0.55

 inse

0.54

infile

0.54

Activations Density 0.386%

occurrences of the word "in" and its variants in different contexts

No Comments

No Known Activations