INDEX

Explanations

terms related to close relationships and connections

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ModelAdmin

-0.95

IsMutable

-0.94

WireFormatLite

-0.93

QMetaType

-0.89

queryInterface

-0.82

ModelForm

-0.82

 Steinberg

-0.79

 Brandt

-0.79

 Berman

-0.78

PhysRev

-0.78

POSITIVE LOGITS

 close

1.60

 Close

1.55

 CLOSE

1.55

CLOSE

1.45

close

1.45

Close

1.40

 Closer

1.35

 Clos

1.33

 closer

1.31

Closeable

1.27

Activations Density 0.061%

terms related to close relationships and connections

No Comments

No Known Activations