INDEX

Explanations

terms that indicate dependency or correlation in mathematical contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

 particulières

-0.57

 migliori

-0.55

 giusta

-0.55

 buono

-0.55

principalTable

-0.54

ARROLL

-0.54

 humanas

-0.52

 intorno

-0.52

UrlResolution

-0.50

parsedMessage

-0.50

POSITIVE LOGITS

 subtly

0.89

 voluntarily

0.87

 quietly

0.86

 spontaneously

0.85

 gently

0.84

 proactively

0.84

 automatically

0.83

 deliberately

0.82

 unconsciously

0.82

 aggressively

0.82

Activations Density 0.722%

terms that indicate dependency or correlation in mathematical contexts

No Comments

No Known Activations