INDEX

Explanations

specific technical terms and definitions related to directed graphical models and their equivalences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

—

-1.12

findpost

-0.87

:✨

-0.85

 propOrder

-0.82

antMatchers

-0.81

 nahilalakip

-0.80

rawtypes

-0.80

NUMX

-0.75

BufferException

-0.75

unately

-0.74

POSITIVE LOGITS

ea

0.86

eb

0.84

ere

0.79

MEC

0.77

es

0.76

CEE

0.75

ed

0.75

 Pele

0.74

et

0.72

 Peas

0.72

Activations Density 5.034%

specific technical terms and definitions related to directed graphical models and their equivalences

No Comments

No Known Activations