INDEX

Explanations

test-related keywords and function calls in code, specifically related to defining and asserting behavior in unit tests

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 Vedi

-0.61

Vedi

-0.61

Vidite

-0.60



-0.59

 يتيمه

-0.58

úgó

-0.58

észetes

-0.58

 Legendre

-0.57

URLException

-0.57

Alpes

-0.57

POSITIVE LOGITS

bumptech

0.57

 perche

0.55

 digitais

0.51

verlag

0.51

érien

0.50

 урна

0.50

 when

0.49

RSpec

0.49

CSRF

0.49

stretchr

0.49

Activations Density 0.049%

test-related keywords and function calls in code, specifically related to defining and asserting behavior in unit tests

No Comments

No Known Activations