INDEX

Explanations

specific patterns or symbols in data strings

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

text after user turn

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

__":

-0.56

ModelSerializer

-0.45

клопе

-0.45

__":

-0.44

principalColumn

-0.44

__':

-0.42

tabular

-0.42

__':

-0.41

\",\

-0.41

ParallelGroup

-0.40

POSITIVE LOGITS

1.41

0.73

0.68

⤹

0.50

 uLocal

0.50

 Monfieur

0.50

 deſt

0.49

omenclature

0.49

큼

0.49

 Leopoldo

0.48

Activations Density 0.000%

specific patterns or symbols in data strings

text after user turn

No Comments

No Known Activations