INDEX

Explanations

the term "SIT" and its various forms and mentions in the text

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

sit sit sit

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

wege

-0.53

%)$

-0.51

endregion

-0.49

 Newman

-0.48

DCC

-0.47

ever

-0.47

 Norma

-0.47

 Mahler

-0.46

 Riccardo

-0.46

 completely

-0.46

POSITIVE LOGITS

Sit

2.06

Sit

2.05

sit

2.03

sit

1.89

SIT

1.66

SIT

1.63

 sits

1.36

 Sitting

1.27

 sitting

1.19

 sitter

1.16

Activations Density 0.014%

the term "SIT" and its various forms and mentions in the text

sit sit sit

No Comments

No Known Activations