INDEX

Explanations

terms related to ranking and classification systems

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ThroughAttribute

-0.82

_('

-0.70

EObject

-0.67

verwijspagina

-0.65

liquer

-0.65

 darbu

-0.65

 onPostExecute

-0.64

PLW

-0.64

 Gaby

-0.64

wiada

-0.62

POSITIVE LOGITS

 RANK

1.39

 Rankin

1.27

rank

1.25

 ranks

1.22

 rank

1.21

 Rank

1.20

Rank

1.18

RANK

1.17

 Ranks

1.16

 ranking

1.15

Activations Density 0.096%

terms related to ranking and classification systems

No Comments

No Known Activations