INDEX

Explanations

terms related to functional relationships and properties in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

 asiático

-0.85

Ingrid

-0.85

 Ingrid

-0.84

 Brice

-0.84

 oocytes

-0.80

dost

-0.77

 Aguirre

-0.73

bride

-0.71

IRT

-0.71

 Bost

-0.70

POSITIVE LOGITS

ional

1.35

AL

1.17

al

1.17

tional

1.12

ial

1.10

sional

1.10

IONAL

0.95

idal

0.94

TemporalType

0.92

inal

0.91

Activations Density 0.311%

terms related to functional relationships and properties in various contexts

No Comments

No Known Activations