INDEX

Explanations

terms related to resistance, particularly in medical and biological 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

});*/

-0.76

 McNally

-0.74

AsUp

-0.72

}},\

-0.71

 alike

-0.70

("]");

-0.70

orianCalendar

-0.70

 folio

-0.69

 McKenna

-0.69

 Deel

-0.69

POSITIVE LOGITS

 resistance

2.35

 Resistance

2.26

 resist

2.14

Resistance

2.10

 RESISTANCE

2.02

resistance

2.01

 Resist

1.97

 RESIST

1.94

 resistances

1.92

 resisting

1.90

Activations Density 0.161%

terms related to resistance, particularly in medical and biological contexts

No Comments

No Known Activations