INDEX

Explanations

programming constructs and declarations 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 @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 doInBackground

-0.78

Efq

-0.76

WSGI

-0.73

 Roskov

-0.72

 Package

-0.71

 PACKAGE

-0.70

 PackageManager

-0.69

Παραπομπές

-0.67

 EconPapers

-0.67

 jsPsych

-0.66

POSITIVE LOGITS

brium

0.53

 import

0.52

0.51

abin

0.49

 util

0.49

 acute

0.47

urd

0.47

itant

0.46

acute

0.46

ahr

0.46

Activations Density 0.063%

programming constructs and declarations in code

No Comments

No Known Activations