INDEX

Explanations

phrases related to design and functionality specifications

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AndEndTag

-0.79

 EconPapers

-0.68

WEBPACK

-0.64

onAttach

-0.63

 يتيمه

-0.61

ThroughAttribute

-0.59

 تانيه

-0.59

aarrggbb

-0.58

 Schall

-0.57

 препратки

-0.56

POSITIVE LOGITS

 designed

1.14

designed

0.95

 Designed

0.88

 suited

0.88

 intended

0.88

 aimed

0.83

Designed

0.82

 destinés

0.78

 geared

0.78

 diseñado

0.78

Activations Density 0.208%

phrases related to design and functionality specifications

No Comments

No Known Activations