INDEX

Explanations

return statements in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

ServiceTest

-0.58

 NDEBUG

-0.57

TextInputLayout

-0.57

…).

-0.55

 TMPro

-0.55

كويكب

-0.53

<bos>

-0.53

—”

-0.52

Cuánt

-0.51

…)

-0.51

POSITIVE LOGITS

 مشين

0.88

0.79

addGap

0.75

ंदीखरीदारी

0.63

Sucesor

0.59

válasz

0.58

 дописавши

0.58

 Promise

0.58

return

0.57

Activations Density 0.048%

return statements in code

No Comments

No Known Activations