INDEX

Explanations

expressions of hypothetical or imagined scenarios

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

imagine hypothetical scenarios

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.20.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

AndEndTag

-0.75

transQ

-0.66

WriteBarrier

-0.65

 betweenstory

-0.65

 okuyayım

-0.62

 arşivlendi

-0.58

tagHelperRunner

-0.57

 referrerpolicy

-0.55

ReusableCell

-0.53

</tfoot>

-0.52

POSITIVE LOGITS

Imagine

0.76

 Imagine

0.69

 imagine

0.56

imagine

0.51

 unimaginable

0.47

 yourself

0.46

 millions

0.43

0.42

 relief

0.40

 reverse

0.39

Activations Density 0.017%

expressions of hypothetical or imagined scenarios

imagine hypothetical scenarios

No Comments

No Known Activations