INDEX

Explanations

numerical comparisons indicating relational expressions in data

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

 onCreateView

-0.66

transQ

-0.62

 hâte

-0.61

Демографія

-0.60

 épais

-0.59

atience

-0.57

 élevées

-0.57

Diweddarwch

-0.57

 preuves

-0.57

Derp

-0.57

POSITIVE LOGITS

aling

0.74

 overlap

0.72

ored

0.67

aled

0.65

ched

0.65

SceneManagement

0.63

allow

0.62

 Inter

0.60

lt

0.57

Inter

0.57

Activations Density 0.095%

numerical comparisons indicating relational expressions in data

No Comments

No Known Activations