INDEX

Explanations

reflexive verbs and phrases indicating personal experience or involvement

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

<start_of_turn> user

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

хьтан

-0.70

 betweenstory

-0.59

最快更新

-0.54

AnimationsModule

-0.48

anjutnya

-0.47

PyTuple

-0.46

yntaxException

-0.45

 dinosaurio

-0.45

 écrit

-0.44

IUrlHelper

-0.44

POSITIVE LOGITS

commons

0.45

 oneself

0.44

 شب

0.43

garden

0.43

 sobie

0.41

 '\\;'

0.40

MeasureSpec

0.40

 Garden

0.39

Garden

0.38

 Yourself

0.38

Activations Density 0.009%

reflexive verbs and phrases indicating personal experience or involvement

<start_of_turn> user

No Comments

No Known Activations