INDEX

Explanations

quantitative measurements and statistical terms related to medical studies

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

<eos>

-0.89

the

-0.57

and

-0.55

“

-0.49

prisingly

-0.48

<i>

-0.46

an

-0.45

<sup>

-0.45

-0.44

POSITIVE LOGITS

Personendaten

0.92

AndEndTag

0.81

 initComponents

0.81

 صوتيه

0.79

 Shakspeare

0.79

Efq

0.78

 Tacitus

0.75

DoubleQuotes

0.75

 Mormons

0.75

Personensuche

0.74

Activations Density 0.830%

quantitative measurements and statistical terms related to medical studies

No Comments

No Known Activations