INDEX

Explanations

punctuation marks, indicating the end of sentences or phrases

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120

Prompts (Dashboard)

24,576 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

 Administrativna

-0.80

WriteTagHelper

-0.71

aarrggbb

-0.68

uxxxx

-0.64

 propOrder

-0.59

NameInMap

-0.57

 linkovi

-0.56

TryDecodeAsNil

-0.54

tvguidetime

-0.54

 nonUne

-0.53

POSITIVE LOGITS

 tartalomajánló

0.46

الحياه

0.40

✎

0.36

GEST

0.36

 mivel

0.35

 palestra

0.35

'])->

0.34

\{\\

0.33

 hạn

0.33

 vermelhas

0.32

Activations Density 0.007%

punctuation marks, indicating the end of sentences or phrases

No Comments

No Known Activations