INDEX

Explanations

occurrences of underscores in code references or identifiers

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

list operations

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

CO

-0.46

 Cronin

-0.45

 Schaefer

-0.45

sendEmail

-0.45

 davidson

-0.45

Autowired

-0.44

HCR

-0.43

GeV

-0.43

SW

-0.42

 superpower

-0.42

POSITIVE LOGITS

 LIST

0.92

 list

0.90

 List

0.89

List

0.82

 lists

0.81

 Lists

0.80

 liste

0.79

 lista

0.79

LIST

0.77

 listes

0.76

Activations Density 0.010%

occurrences of underscores in code references or identifiers

list operations

No Comments

No Known Activations

occurrences of underscores in code references or identifiers

list operations

No Comments

No Known Activations