INDEX

Explanations

geographical locations and names

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

windowFixed

-0.62

and

-0.57

stateProvider

-0.57

photobucket

-0.57

ffions

-0.54

 nahilalakip

-0.53

pakt

-0.52

TRAILING

-0.50

+:+

-0.49

 BoxDecoration

-0.49

POSITIVE LOGITS

 Tiberius

0.54

ConstraintMaker

0.54

 Thebes

0.52

 Charlemagne

0.52

ьа

0.51

 préc

0.51

WritableDatabase

0.51

 Cæsar

0.51

فحة

0.51

☏

0.50

Activations Density 0.119%

geographical locations and names

No Comments

No Known Activations