INDEX

Explanations

function return statements in code

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

return path

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.31.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

piecz

-0.41

 kayna

-0.38

 unters

-0.38

Зачем

-0.37

 regularmente

-0.33

 pequenos

-0.32

 réguli

-0.32

 gevol

-0.32

 élas

-0.32

 piccoli

-0.32

POSITIVE LOGITS

RegressionTest

0.83

 Infórmanos

0.73

 initComponents

0.71

 onCreateView

0.70

 nakalista

0.66

IntoConstraints

0.66

principalTable

0.66

 Signalez

0.64

WebElementEntity

0.63

ParallelGroup

0.61

Activations Density 0.001%

function return statements in code

return path

No Comments

No Known Activations