INDEX

Explanations

function definitions and declarations in programming code

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

creature position flags

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

principalTable

-0.47

IntoConstraints

-0.46

hdessä

-0.45

 procedentes

-0.44

 plufieurs

-0.44

MessageOf

-0.43

 Kebijakan

-0.43

Fordítás

-0.43

 råd

-0.43

 gemens

-0.43

POSITIVE LOGITS

 Movement

0.44

0.42

andExpect

0.41

MigrationBuilder

0.40

skr

0.39

 movement

0.38

*/].

0.38

 Poss

0.37

INSEE

0.36

PPA

0.36

Activations Density 0.009%

function definitions and declarations in programming code

creature position flags

No Comments

No Known Activations