INDEX

Explanations

author names and their affiliations, particularly in academic references

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

{§

-0.54

 entrer

-0.53

TypedDataSet

-0.51

migrationBuilder

-0.51

 gjen

-0.49

tokio

-0.48

setHas

-0.48

 kasarigan

-0.48

Clik

-0.48

 oprot

-0.48

POSITIVE LOGITS

}))

0.70

IntoConstraints

0.65

alyptus

0.58

}),

0.56

 سكانية

0.54

*/;

0.52

 demografica

0.52

uminense

0.52

UnusedPrivate

0.51

utenants

0.51

Activations Density 0.447%

author names and their affiliations, particularly in academic references

No Comments

No Known Activations