INDEX

Explanations

terms related to physical abilities and disabilities, particularly in the context of movement and motor control

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

endpush

-0.60

rief

-0.57

StoryboardSegue

-0.55

Портал

-0.54

 समीक्षाएं

-0.53

lottesville

-0.53

neval

-0.52

Espèce

-0.51

Alike

-0.50

}{*}{

-0.50

POSITIVE LOGITS

 skills

0.70

 dexterity

0.69

skills

0.65

ISupport

0.61

WriteBarrier

0.60

TagMode

0.58

 skill

0.58

 useRouter

0.56

ChildScrollView

0.56

ordination

0.56

Activations Density 0.345%

terms related to physical abilities and disabilities, particularly in the context of movement and motor control

No Comments

No Known Activations