INDEX

Explanations

scientific terms related to biochemical processes and properties

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

Население

-0.59

ämään

-0.55

orological

-0.52

 typelib

-0.52

hdys

-0.51

 мәгълү

-0.49

InstanceState

-0.48

setContentView

-0.48

IBUS

-0.48

隈

-0.48

POSITIVE LOGITS

 capability

2.39

 ability

2.31

 capabilities

2.26

 abilities

2.13

 capacity

2.08

 capacities

1.89

能力

1.83

 Capabilities

1.81

 Capability

1.78

 Ability

1.76

Activations Density 0.719%

scientific terms related to biochemical processes and properties

No Comments

No Known Activations