INDEX

Explanations

place names and geographic features

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

 such

-0.54

fulness

-0.54

AutoField

-0.54

 estekak

-0.53

BagConstraints

-0.53

testcase

-0.52

 "'");

-0.51

ituary

-0.50

 <=",

-0.49

aben

-0.49

POSITIVE LOGITS

expandindo

0.73

 Exactos

0.70

 INTERESAR

0.69

 district

0.69

 District

0.61

 municipalité

0.61

 slipper

0.60

onedDateTime

0.57

conexion

0.56

district

0.55

Activations Density 0.172%

place names and geographic features

No Comments

No Known Activations