INDEX

Explanations

phrases and terms related to academic and scientific comparisons and evaluations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

MessageTagHelper

-0.44

Nazionale

-0.43

 disesuaikan

-0.40

 Vorge

-0.39

 recurrir

-0.39

__*/

-0.39

providedIn

-0.38

poli

-0.37

 Kampagne

-0.37

POSITIVE LOGITS

 reinen

0.90

 onCreateView

0.83

Portail

0.74

揄

0.73

FormTagHelper

0.72

extAlignment

0.71

ValueStyle

0.71

ValueGeneration

0.71

irected

0.68

 outright

0.68

Activations Density 0.694%

phrases and terms related to academic and scientific comparisons and evaluations

No Comments

No Known Activations