INDEX

Explanations

terms related to various communication protocols

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

Efq

-1.00

lectricité

-0.90

voir

-0.88

 Monfieur

-0.81

 Mahabhar

-0.80

 fhew

-0.80

 Jefus

-0.79

 becauſe

-0.78

 poffe

-0.77

 Voir

-0.76

POSITIVE LOGITS

 Proto

0.97

 Martin

0.91

 PROTO

0.90

Proto

0.88

 protocols

0.87

Martin

0.85

 PROTOCOL

0.84

findpost

0.81

WriteLiteral

0.80

 protocol

0.78

Activations Density 0.129%

terms related to various communication protocols

No Comments

No Known Activations