INDEX

Explanations

function calls and memory allocation related to data structures

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

plan(8) Capacity

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

CreateModel

-0.47

 createSlice

-0.43

AutoField

-0.42

InjectAttribute

-0.39

 MainAxisSize

-0.36

 розташо

-0.36

 reform

-0.35

MessageTagHelper

-0.35

 feroit

-0.34

 finnas

-0.34

POSITIVE LOGITS

GEBURTSDATUM

0.47

unft

0.44

 neceffary

0.43

 intptr

0.43

 compromis

0.43

urnum

0.42

 maga

0.42

edale

0.41

 ſmall

0.41

 aufnehmen

0.41

Activations Density 0.004%

function calls and memory allocation related to data structures

plan(8) Capacity

No Comments

No Known Activations