INDEX

Explanations

instances of notable discoveries or historical findings

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

énier

-0.57

 beginnetje

-0.56

 AssemblyTitle

-0.55

LookAnd

-0.51

 resourceCulture

-0.50

 szóci

-0.50

ніципа

-0.49

ThemeOverlay

-0.49

ocellular

-0.48

Rujuakan

-0.48

POSITIVE LOGITS

 discovered

1.00

 Discovered

0.90

 discoveries

0.89

 discovery

0.87

 Investigation

0.87

 investigation

0.85

 Investigations

0.83

 investigations

0.82

discovered

0.81

investigation

0.80

Activations Density 0.952%

instances of notable discoveries or historical findings

No Comments

No Known Activations