INDEX

Explanations

annotations and parameters within code documentation

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

<bos>

-0.62

rcParams

-0.47

TestMethod

-0.46

)))),

-0.46

Anhalt

-0.45

GeneratedCode

-0.45

${\

-0.45

/*---

-0.44

 Accesat

-0.44

UnitTesting

-0.42

POSITIVE LOGITS

 string

1.05

string

0.97

 boolean

0.93

boolean

0.89

 number

0.79

 object

0.79

 Monfieur

0.74

 mixed

0.74

 strings

0.73

 integer

0.70

Activations Density 0.227%

annotations and parameters within code documentation

No Known Activations