INDEX

Explanations

words related to programming constructs and data structures

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

GEBURTSDATUM

-0.82

endregion

-0.57

ciety

-0.56

 gyhoeddwyd

-0.52

verwijspagina

-0.51

SuspendLayout

-0.51

pur

-0.50

Me

-0.49

marily

-0.49

Beb

-0.49

POSITIVE LOGITS

 verrez

0.84

Autoritní

0.82

 HasFactory

0.82

 becauſe

0.78

 Diſ

0.77

 ſhall

0.76

 reaſon

0.75

 whoſe

0.74

 preſent

0.74

 ſever

0.72

Activations Density 0.341%

words related to programming constructs and data structures

No Comments

No Known Activations