INDEX

Explanations

references to characters and elements from "Alice in Wonderland."

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

Alice, Queens, Carroll, Wonderland

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

 Signalez

-0.57

findpost

-0.57

phosa

-0.55

 esternos

-0.52

IsMutable

-0.50

upol

-0.50

SharedDtor

-0.49

 ModelExpression

-0.48

mybatisplus

-0.47

IVEREF

-0.46

POSITIVE LOGITS

 Wonderland

0.63

 wonderland

0.52

 Alice

0.51

Alice

0.48

 alice

0.44

 ALICE

0.42

alice

0.40

ALICE

0.40

 Universitaria

0.38

 surreal

0.37

Activations Density 0.007%

references to characters and elements from "Alice in Wonderland."

Alice, Queens, Carroll, Wonderland

No Comments

No Known Activations