INDEX

Explanations

punctuation marks in the text

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

user or <start_of_turn>

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

SequentialGroup

-0.34

 CreateTagHelper

-0.32

 sentado

-0.30

 married

-0.30

 shot

-0.29

 experience

-0.29

 poll

-0.28

sepeda

-0.28

://

-0.28

 voluntarily

-0.27

POSITIVE LOGITS

CppMethod

0.65

$_"

0.64

BufferException

0.62

PerformLayout

0.61

 Models

0.60

 ब्रेकडाउन

0.60

 <<<<<<<<<<<<<<

0.58

<unused16>

0.58

<unused8>

0.58

[@BOS@]

0.58

Activations Density 0.003%

punctuation marks in the text

user or <start_of_turn>

No Comments

No Known Activations