INDEX

Explanations

sections or headings related to procedure and historical background in documents

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

<bos>

-0.52

(\

-0.49

 inter

-0.48

all

-0.48

tamin

-0.47

ta

-0.47

de

-0.47

 them

-0.46

va

-0.45

POSITIVE LOGITS

rungsseite

1.07

 EconPapers

1.03

 kasarigan

1.02

__":

0.97

__':

0.96

 AssemblyCulture

0.93

 initComponents

0.89

 referenties

0.87

 resourceCulture

0.86

 Roskov

0.83

Activations Density 0.288%

sections or headings related to procedure and historical background in documents

No Comments

No Known Activations