INDEX

Explanations

instances of the word "designated" and related terms indicating specific roles or classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 صوتيه

-0.73

 Signalez

-0.67

icoot

-0.66

addCriterion

-0.64

ValueStyle

-0.64

GEBURTSDATUM

-0.59

 Италијани

-0.57

 jadx

-0.57

SourceChecksum

-0.55

 eventName

-0.55

POSITIVE LOGITS

 assigned

0.93

 designated

0.83

 stats

0.74

 allocated

0.71

designated

0.70

 Assigned

0.70

Designated

0.67

 Stats

0.66

assigned

0.64

 Designated

0.63

Activations Density 0.163%

instances of the word "designated" and related terms indicating specific roles or classifications

No Comments

No Known Activations