INDEX

Explanations

references to locations, particularly in a context related to navigation or mapping

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 koncentr

-0.62

 jsPsych

-0.53

DoesNotExist

-0.53

ThroughAttribute

-0.52

Active

-0.52

JpaRepository

-0.51

struzione

-0.51

 Determines

-0.50

 Concentr

-0.50

 artesanía

-0.49

POSITIVE LOGITS

 covered

1.54

 coated

1.36

 decorated

1.36

 adorned

1.34

 equipped

1.18

 Covered

1.16

 decked

1.11

Covered

1.06

 clad

1.05

 dressed

1.03

Activations Density 0.585%

references to locations, particularly in a context related to navigation or mapping

No Comments

No Known Activations