INDEX

Explanations

references to system calls or logging statements in programming code

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

System. namespace expressions

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

Negative Logits

 CreateTagHelper

-0.55

 émer

-0.45

 Aufla

-0.44

 plazos

-0.44

guantes

-0.43

BufferException

-0.43

 honra

-0.42

sividad

-0.42

 adquis

-0.42

 loadData

-0.42

POSITIVE LOGITS

LLocation

0.54

Lähteet

0.47

CFS

0.46

 publick

0.45

RTEX

0.45

mmm

0.44

 Ganga

0.44

endpush

0.43

 console

0.43

 Pergamon

0.43

Activations Density 0.002%

references to system calls or logging statements in programming code

System. namespace expressions

No Known Activations