INDEX

Explanations

words related to biological entities and technical components

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

Followed by words indicating a part of an object

np_acts-logits-general · gemini-2.0-flash

its or itself

np_acts-logits-general · gemini-2.5-flash-lite

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

transQ

-0.65

 resourceCulture

-0.64

 '\\;'

-0.64

adaptiveStyles

-0.63

Personensuche

-0.62

 createState

-0.61

UnsafeEnabled

-0.61

UnknownFields

-0.60

@"/

-0.59

}());

-0.57

POSITIVE LOGITS

 itself

0.74

 SqlCommand

0.64

its

0.62

 molecule

0.62

ITS

0.61

Its

0.57

its

0.56

 unit

0.55

 corps

0.53

initComponents

0.53

Activations Density 1.567%

words related to biological entities and technical components

Followed by words indicating a part of an object

its or itself

No Comments

No Known Activations