INDEX

Explanations

variations of the root word "comp" related to complexity or processes

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

(!__

-0.79

AutoScaleMode

-0.75

 tartalomajánló

-0.75

 minOccurs

-0.74



-0.73

Cyfeiriadau

-0.72

EndTag

-0.72

iriman

-0.72

ginate

-0.68

ibição

-0.68

POSITIVE LOGITS

Comp

1.91

 Comp

1.85

comp

1.85

COMP

1.73

 comp

1.70

 COMP

1.70

 comps

1.61

COM

1.38

COM

1.35

comps

1.33

Activations Density 0.107%

variations of the root word "comp" related to complexity or processes

No Comments

No Known Activations