INDEX

Explanations

phrases or contexts that indicate groups, connections, or relationships among entities

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

ngdoc

-0.89

 itſelf

-0.87

MLLoader

-0.85

 ſeveral

-0.82

Personendaten

-0.82

InputBorder

-0.81

arraycopy

-0.79

 myſelf

-0.78

Efq

-0.78

drawal

-0.78

POSITIVE LOGITS

putan

0.47

 this

0.46

 including

0.44

this

0.44

שם

0.43

 okolí

0.42

il

0.40

 tarifas

0.40

Mantenimiento

0.40

Initializable

0.40

Activations Density 0.741%

phrases or contexts that indicate groups, connections, or relationships among entities

No Comments

No Known Activations