INDEX

Explanations

sequences of numerical values and identifiers

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.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

quia

-0.51

Illust

-0.47

oudre

-0.47

pand

-0.46

 lộ

-0.45

 Lore

-0.45

',

-0.45

Res

-0.43

Tet

-0.43

POSITIVE LOGITS

bootstrapcdn

1.13

enumii

1.05

EndContext

0.99

ViewFeatures

0.95

Geplaatst

0.95

WithIOException

0.92

ScopeManager

0.91

StructEnd

0.87

 Paglinawan

0.86

COUVER

0.86

Activations Density 0.855%

sequences of numerical values and identifiers

No Comments

No Known Activations