INDEX

Explanations

mentions of the name "Kate" and tracks constants in coding contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

UnusedPrivate

-1.04

DockStyle

-0.87

 Roskov

-0.87

 <>",

-0.87

mobileqq

-0.85

 Upan

-0.82

GraphicsUnit

-0.81

 Italijanski

-0.80

 myſelf

-0.79

DllImport

-0.78

POSITIVE LOGITS

We

0.63

href

0.56

0.55

 come

0.54

we

0.54

ka

0.53

0.52

We

0.52

 think

0.50

 care

0.50

Activations Density 0.203%

mentions of the name "Kate" and tracks constants in coding contexts

No Comments

No Known Activations