INDEX

Explanations

sequences of numbers or patterns 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 @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 disambiguazione

-0.86

 tori

-0.84

 Boogie

-0.82

 Legg

-0.78

 Karak

-0.78

Portail

-0.78

ARA

-0.77

 Portail

-0.77

ARI

-0.76

PRT

-0.75

POSITIVE LOGITS

1.95

1.21

SIX

1.20

Six

1.19

⁶

1.18

６

1.11

1.07

SIX

1.05

six

1.05

 Sixth

1.04

Activations Density 0.692%

sequences of numbers or patterns in data

No Comments

No Known Activations