INDEX

Explanations

references to attached files or 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

 GenerationType

-0.74

rocco

-0.73

addGap

-0.72

 colspan

-0.72

MemoryWarning

-0.71

 glyphicon

-0.66

Rama

-0.62

awtextra

-0.62

urgeon

-0.61

 textStatus

-0.61

POSITIVE LOGITS

 ATTACH

1.59

 Attach

1.55

 attachment

1.51

 attachments

1.50

 attaches

1.47

attach

1.46

 attached

1.45

 attach

1.45

 Attachment

1.44

 attaching

1.42

Activations Density 0.135%

references to attached files or documents

No Comments

No Known Activations