INDEX

Explanations

phrases indicating a need or demand for specific methods or systems

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

 onCancelled

-0.66

sizeCache

-0.59

InitVars

-0.55

efeller

-0.54

 ſtate

-0.54

CppMethod

-0.53

 deſt

-0.51

orElseThrow

-0.50

 IndexPath

-0.49

ниципа

-0.49

POSITIVE LOGITS

 propOrder

0.57

 AssemblyCulture

0.55

 dependable

0.54

 trustworthy

0.53

Izvori

0.52

 дописавши

0.51

expandindo

0.51

 reliable

0.51

 ddelweddau

0.50

фициаль

0.49

Activations Density 0.289%

phrases indicating a need or demand for specific methods or systems

No Comments

No Known Activations