INDEX

Explanations

mentions of geographic locations and associated entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

SBATCH

-0.80

bootstrapcdn

-0.70

jsii

-0.62

 ujednoznacz

-0.60

Tikang

-0.60

uxxxx

-0.59

 intptr

-0.57

Ngb

-0.57

baric

-0.56

SequentialGroup

-0.55

POSITIVE LOGITS

 Montana

0.76

 Missoula

0.74

Montana

0.69

 Kalis

0.68

 Flat

0.63

 Billings

0.63

 Havre

0.58

 Ronan

0.57

 Helena

0.57

Flat

0.57

Activations Density 0.229%

mentions of geographic locations and associated entities

No Comments

No Known Activations