INDEX

Explanations

numerical data or coded representations of information

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

<start_of_turn>user or code fragment

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

 asimismo

-0.45

 conmigo

-0.37

RegressionTest

-0.37

 burbujas

-0.35

 vecind

-0.33

новниш

-0.32

 tambin

-0.31

 crossorigin

-0.31

 sepen

-0.31

 infine

-0.30

POSITIVE LOGITS

 initComponents

0.69

Personendaten

0.60

 للمعارف

0.59

IContainer

0.56

ftagPool

0.55

andExpect

0.54

ScopeManager

0.54

ьаж

0.53

UIControlState

0.52

ConstraintMaker

0.51

Activations Density 0.000%

numerical data or coded representations of information

<start_of_turn>user or code fragment

No Comments

No Known Activations