INDEX

Explanations

sequences of scientific and medical terminology related to analyses and treatments

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

sequence

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

 kaarangay

-0.49

GEBURTSDATUM

-0.49

Hentet

-0.49

 незавершена

-0.48

aarrggbb

-0.47

SharedCtor

-0.46

ValueStyle

-0.46

migrationBuilder

-0.44

CodeAttribute

-0.44

zeum

-0.44

POSITIVE LOGITS

 successive

0.75

 sequentially

0.70

 successively

0.66

 sequential

0.52

 suces

0.51

 kolejne

0.47

 progressively

0.45

ngdoc

0.43

 consecutive

0.43

Different

0.43

Activations Density 0.238%

sequences of scientific and medical terminology related to analyses and treatments

sequence

No Known Activations