INDEX

Explanations

statements related to legal or financial issues

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

ftagPool

-0.58

 almost

-0.57

 Almost

-0.56

almost

-0.53

意外と

-0.53

 cheap

-0.52

 måske

-0.52

 sneaky

-0.52

 screamed

-0.52

Almost

-0.51

POSITIVE LOGITS

verständlich

0.82

 neceff

0.82

eraard

0.81

 fubject

0.80

 Majefty

0.79

 neceffary

0.77

 ſeveral

0.76

 naturlig

0.74

 regrettable

0.74

 itſelf

0.74

Activations Density 0.271%

statements related to legal or financial issues

No Comments

No Known Activations