INDEX

Explanations

symbols and formatting indicators in a document

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 previous

-0.93

previous

-0.77

Previous

-0.75

 PREVIOUS

-0.71

 предыду

-0.71

PREVIOUS

-0.70

 sebelumnya

-0.70

 Previous

-0.68

 prior

-0.67

 previously

-0.67

POSITIVE LOGITS

abestanden

0.91

 Normdatei

0.79

 disambiguazione

0.78

 ProtoMessage

0.75

 виправивши

0.74

 ffilmiau

0.72

 Vikipedi

0.70

parsedMessage

0.69

TagMode

0.66

 سكانية

0.66

Activations Density 0.441%

symbols and formatting indicators in a document

No Comments

No Known Activations