INDEX

Explanations

desires and wants expressed in relation to personal choices and preferences

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

AddTagHelper

-0.85

XmlAccessorType

-0.85

AccessorTable

-0.79

InputTagHelper

-0.78

ScopeManager

-0.77

DoubleQuotes

-0.75

elemField

-0.75

ItemBackground

-0.74

AndEndTag

-0.73

DockStyle

-0.73

POSITIVE LOGITS

대로

0.49

dorf

0.47

róleo

0.46

бычно

0.45

ogeneous

0.44

">//

0.43

 getNum

0.43

initState

0.43

own

0.42

يدة

0.42

Activations Density 0.153%

desires and wants expressed in relation to personal choices and preferences

No Comments

No Known Activations